cd /tmp
# Get the Prism macOS runtime
curl -fL https://github.com/PrismML-Eng/llama.cpp/releases/download/prism-b10685-7dffb15/llama-prism-b10685-7dffb15-bin-macos-arm64.tar.gz -o bonsai-runtime.tar.gz
tar -xzf bonsai-runtime.tar.gz
# Get the ~5.95 GB GGUF model:
curl -fL https://huggingface.co/prism-ml/Ternary-Bonsai-2-27B-gguf/resolve/main/Ternary-Bonsai-2-27B-PTQ1_0.gguf -o Ternary-Bonsai-2-27B-PTQ1_0.gguf
# Run the server, I used port 8331
./llama-prism-b10685-7dffb15/llama-server \
-m Ternary-Bonsai-2-27B-PTQ1_0.gguf \
--port 8331 -ngl 99 -fa on -c 32768
Then open http://localhost:8331 for the (very good) baked in llama-server web UI... or run a prompt via the API like this:
uvx llm openai endpoint http://127.0.0.1:8331/v1 \
--model bonsai-2-27b --responses hi
That's running at ~20 token/second for me on an M5 Pro (after a server restart I got 44 token/second, not sure why), but I'm pretty sure something isn't working right, on startup the server said "ggml_metal_device_init: - the tensor API is not supported in this environment - disabling".
I managed to run it with RTX 3070 (8GB VRAM) following the "Quickstart" on HF model card with minor modifications (modify the architecture 86 for your own hardware):
If you want to download the gguf to your regular huggingface cache directory instead of to /tmp, you can download the model and run the server in one step:
export HF_TOKEN=xxx # optional, speeds up the download
./llama-prism-b10685-7dffb15/llama serve \
-hf prism-ml/Ternary-Bonsai-2-27B-gguf:PTQ1_0 \
--port 8331 -ngl 99 -fa on -c 32768
Thanks for all of your exploration in public Simon.
Commenting because the fix I proposed was merged in roughly 49 commits after the PrismML Fork. The “tensor API is not supported” warning occurred because llama.cpp’s startup probe fails to compile a matmul2d kernel: Metal’s tensor headers require language version 4.0, but ggml-metal-device.m previously omitted MTLCompileOptions.languageVersion, disabling the API universally.
Yeah just wanted to mention in case it explains the 2x lower throughout you are seeing on M5. To be fair their documentation is a bit inconsistent in some spots.
Would be good to know if the release and weights from their demo repo work better. I’m trying on a 4090 and will report back.
Let’s see, so if you get the same 1/9th the size compression ratio with GLM-5.3-Flash, then you’d end up with a ~72GB model that’s about as good as GPT-5.6 Sol (high), according to artificialanalysis.ai
Which is within reach of some higher end consumer hardware, especially with layer offloading.
You have to wonder what kind of trouble the “labs” are in when this is becoming possible. Lots of money, where’s the moat?
There's a chap called Bijian Bowen who does very quick agentic coding challenges for new models (very soon after release!) mainly for toy games or websites. He just did one for this model and included a comparison with the base model Qwen 3.8 which shows the "near-lossless" claim should be taken with a grain of salt. It is an interesting model if you are GPU starved and want local, but you might have trouble finding things it is good at.
I really wish people would stop saying N times smaller than something when making a comparison; that makes no sense - it's 1/9th (11.11%) the size. You don't get a smaller quantity by multiplying by a number greater than 1.0. You could instead reverse the subjects being compared - "the original model is 9x bigger than this new smaller, efficient model" or some such. That makes sense.
I keep seeing this being used when people talk about efficiency or performance gains and it's just very unintuitive language.
I agree it makes little sense in a literal mathematical take but "it's 9x smaller" or is too much of linguistic advantage compared to "the original is 9x larger" or "it's 1/9th as large" to expect a change with. You don't have to invoke fractions, it keeps the thing in focus as the first subject, it matches the pattern of the inverse statement, and it's just plain short... so that's what people will adapt and interpret the meaning to be.
One other way to map both types of linguistic statement consistently to math is to interpret "9x" as "there is a 9 times difference between these two things" and then "smaller"/"larger" tells you which end of that separation the subject is (rather than specifying whether the multiplication builds up or down).
11% is also a really saying a fraction, 11 per-cent or 11/100, but there's nothing wrong with that feeling more natural to some and it is at least a nice shorthand way for the written form. "A ninth the size" is a similar alternative. All are really fine, there's always someone who has trouble with a given representation compared to another.
If we were talking about speed instead of size, i think it would be perfectly reasonable to say 9x faster. I'm not sure I agree that 9x smaller is unintuitive. It makes sense to me.
"Nine times" literally means multiplied by nine, but here we're dividing by nine. It's not unintelligible (because the corrupted verbiage is so commonplace) but it is needlessly awkward. Like saying "resulted in a size reduction increase of 10 megabytes."
Rather, "nine times larger" means multiplied by nine, and "nine times smaller" means divided by nine. This is basic and not particularly awkward, certainly not more so than e.g. positive/negative correlation, or many much more awkward and more common linguistic constructions, IMO.
If you have to edit out words (i.e. context) to argue a phrase doesn't make sense... I am not sure what mental model you have for natural language, exactly, but it certainly isn't a very robust one.
"faster" relates to speed. Speed is related to time and speed of a thing is usually defined by time. 9x faster speed translates to time/9. There is an extra step of related conversion there.
Conversely, 9x [filesize/natural number] is bigger. Every time. At least in the basic maths used by most people. There is no conversion into other units.
Therefore "9x smaller" when talking about a natural number like filesize is a nonsense statement in logic terms. If you strive for unambiguous phrasing - which is a significant part of the programming experience - this logical nonsense might well perturb you.
But english language is a flexible thing and if the phrase communicates your intent to your audience then that's fine by me.
I think more intuitively for speed - you are multiplying the things per period. If I’m making widgets 9x faster I have 9 x the previous number of units per period of time. To get the amount of time, you invert the ratio to period over units.
Multiplying some scale by units per period makes sense and is both linguistically and mathematically sound.
They probably rephrased it from some more technical form like "we compressed the model by a factor of 9" or "we've improved the packing efficiency of the model by 9x". Where these are measurements of the transformation the model is undergoing, not measurements of the resulting model.
This sounds like the same kind of error as writing "0.10 cents" because it's less than a dollar when the number is in dollars regardless of how big or small it is
Eh, when I read smaller with an integer multiplier, I mentally switch to the reciprocal. Easier than convincing the world not to use "9x smaller". Do you feel the same way about "9x faster"? What you're actually measuring is time, and "faster" is the reciprocal of time, similarly to "smaller" being the reciprocal of size.
yes, actually I do think the phrase 'N times faster' is sensible and logical
if I say 'this Apple M5 chip is 3x faster' than this intel chip, it implies two things:
- the run time of most operations that runs on it is now reduced (so one quantity is smaller)
- but also: MORE WORK is being completed per unit of time compared to the intel chip (so this quantity is greater)
So yes, a greater quantity is being measured in the apple chip compared to the intel when you say apple is N times faster.
i guess this a quirk with the word 'faster' - it actually measures two things, time and work performed per unit of time. the word smaller just measures size.
like, if I give a customer a cup of coffee one day, then give them a SMALLER cup of coffee the next day, for the same price, but declare "It's now 2X more space efficient!" i.e. it's now half the size, I'm certain the customer is gonna be pissed.
Ah, but in this case the customer is buying the coffee for the caffeine content. And you've doubled the caffeine content per volume! Twice as efficient a delivery mechanism, similar to this model!
> Ternary Bonsai 2 27B uses ternary {−1, 0, +1} weights with FP16 group-wise scaling, for 1.76 effective bits per weight
If I recall correctly, a recent post [1] has shown that Q2 quants (with like 2.6 bpw) of the same base Qwen model sit at the edge between "noticeably worse" and Q1's "useless". I took a quick glance at Bonsai's blog posts, and don't really see them comparing themselves to "typical" quants or explaining what's the special sauce that makes them better?
I wonder how well it performs in practice, because I can't help seriously doubting those benchmarks. That would put this 6GB model in Opus 4.6+ ballpark. Granted, that's mostly to Qwen 3.8's credit, but it's hard to believe that Qwen's already unbelievable capability density can still be compressed this much more.
I think the general idea is naive quantization falls apart below 4bpw but you can go lower with more sophisticated QAT-adjacent methods. Bonsai's quantization method is proprietary though.
That's correct. I think there can certainly be issues even with 4bpw with naive quantization (IE you'll notice far better results from a QAT 4bpw vs a naive 4bpw).
One such method that I've been meaning to look into further is Tencent's AngelSlim QAT/PTQ approach. They did a Hy4 preview release thats an STQ_1_0 at 2.38 bpw:
Of course, it's still 213g of VRAM I'd need so it's somewhat out of the range of what I can run locally. In contrast, this new Bonsai is nice because the original was already exciting for making use of low VRAM devices. Could breath new life into some of the older GPUs that were previously close to top of the line just quite VRAM constrained by modern standards and still quite cost effective for now.
1.76 bpw number is kinda misleading if you compare it directly to IQ2/Q2. The encoding is ternary, but the quantization procedure is way more sophisticated than "round Qwen weights to {-1,0,+1}."
They rotate the weights into a quantization-friendly basis first, then ternarize with per-group scales and error compensation.
The benchmarks they chose are rather cherry picked to not include long context or difficult ones that involve long horizon work or many agent turns, as I suspect this is where the model shows more differences compared to the full fat one
Yep more hops from the lower Q is likely going to skew the vectors further over time.
I wonder if there's a way to mitigate this by running it through an original Q8 draft model, attuned somehow for the PTQ1 quant, but giving it a higher threshold for the acceptance linear with the context length itself?
The longer the context, the higher the multiplier on the threshold, and more likely the draft result is used. Not ideal but it may extend the usable max context.
This model might, even without this, be amazing for short lived agents that work via generations / have changing tasks.
Came to ask the same. From my really rough understanding, it seems like Unsloth's method allows a slightly higher precision at a higher file size, while PrismML's uses a different approach to achieve a smaller size (and presumably less precision).
What is never totally clear with a lot of these releases is the scope of what it's good at. Models that can run with good speed on affordable consumer hardware for coding only is the dream. I am never going to use this for writing, images, or "general knowledge". Coding only
Love this for the folks with 16gb graphics cards - 3.8 27b has been incredible but not quite runnable on anything less than 32gb - will try loading this up on my 16gb intel b50 and see how it goes - not sure these quants can be accelerated by the XPU cores yet but maybe in time!
I run qwen 27b on an old-ass 16gb gpu. It’s very possible using unsloth 2bit and 3bit quants, tho there are a bunch of interesting quants that let you run closer to 4bit on 16gb. This article that’s currently also on the front page mentions a bunch of them while discussing their own quant https://byteshape.com/blogs/Qwen3.8-27B/
You can run the ~4 bit quant(s) on 24gb, if you're not _too_ picky on context size.
This will hopefully be better, though it'd be a _very_ surprising increase in performace at the size they say. Would love to see more about how it benchmarks.
I run Unsloth's UD-Q4_K_S on 20 GB of VRAM (RX 7900 XT) and I get ~90k tokens of context without quantizing KV cache. With 8-bit quantization, I get about a 134k token context window. That's with only one slot, but for me, it works pretty darn well, with 20-35 tok/s depending on how full that window is.
7900 XT is a sleeper card. When I initially bought it, it was priced at the lowest wattage per $ per GB VRAM (not normalized for token speeds...) Although I ended up swapping for the XTX because that 4GB means everything in just increasing the context window. At 8bit KV my window is over 200k, and although qwen3.8 loves vomiting out tokens as part of its reasoning chain I trust it enough to get assigned tasks done eventually, which I could not say of any model before its release.
How has software/driver support been? I got burned hard by AMD last generation or the one before. Things smoother now, or do you have to baby it like hell and pick and choose software that works?
I don't do anything fancier than inference, and I only use llama.cpp, which supports rOCM. I've had few issues; most GGUFs I download work right out of the box. Nearly any popular model has a quant that just works. But as you can see I don't use my GPU for anything weird or nonstandard.
You can trivially run 131k on 24GB 4bit, and there are repos with tweaks that allow you to get the full 262k but idk if there's degradation with their approach.
I'm doing the same with a context of about 128-150k Surprisingly, I get subjectively better results with Unsloth's 3 bit quants (UD-Q3-XL something), than their 4 bit quants (S or M)
I'm hoping they release an 8B v2 based on the Qwen 3.8 series in the near future - that would give us a really powerful model that could be run directly on users phones.
~100t/s prefill, ~15t/s, dropping to ~10t/s later with 64k context.
The issue is I have yet to find a useful agentic local llm that I can run on this machine.
Just given a relatively simple task on a swift app, took 25 minutes, brainstorming like crazy but can not decide on what to do. Eventually I killed it. GPT 5.6 sol-medium took 3 minutes to complete the same task for reference.
Gemma 30B with 256K context runs at 20 tok/sec on my M3 Max with 128GB RAM so I think there’s something wrong with your setup. This should run at ~30-40 toks. Maybe your inference engine is not optimised for Mac.
then used it in a very minimalistic pi with a very small system prompt.
Didn't spend much time to try to optimize it tbh, but my issue was not the speed. it just could not make a decision on how to implement the task, kept going on an on.
I tried this one, but I found Ornith1.5 to be a better MoE model for me, also very fast. But I still couldn't make it implement a real task on a real repo :( it only worked with an extremely clear directions and very small tasks.
I tried their WebGPU version and it immediately started looping. Yeah "near lossless" my ass. Plus the reasoning that it looped on was clearly wrong and unlike the non quantized 27B
I wonder how their talks with Apple went. Having this run on the TPU opposed to just the GPU, which drains a significant amount of battery life by comparison, is what I'm really interested in.
Cautiously optimistic. The V1 was noticeably weak on world knowledge but here the 3.8 base model is geared more towards reasoning than world knowledge anyway so might not matter as much
GPT Astra did some benchmarking on the DGX Spark. Speed: 34.38 tokens/sec for generation.
Seems like we don't have a drafter model yet so it could not test with speculative decoding on. ngram speculative decoding did not help too much either - not enough accepted tokens.
Smaller size I suppose does not mean better performance in this case - we maybe limited by Spark's low memory bandwidth.
That's a rough place to land on a spark. It seems unlikely to be memory bandwidth at this model size, but maybe just lack of tuned kernels? The chip is missing some CUDA features but with tuning you should be able to hit way more than that even without a drafter.
I was wondering if those ternary bits get expanded into full floats internally in the kernels - you’re probably right about lack of tuned kernels. I’m not sure you could just tune your way out of that easily though. Any suggestions on trying particular solutions?
LLM quants seem to eerily converge to modern/not so modern graphics techniques. You wouldn't think it would apply but it's obvious in hindsight. In fact mining graphics ideas is probably a good inspiration for efficient LLM architecture.
For example, the Hadamard activation transform used here feels a lot like multiplying
Fourier basis ala DFT; strong parallels to how image codecs work to make the residuals more compressible (especially discrete block codecs like are used in GPU compressed textures).
I thought I was being clever suggesting that you could even abuse texture decode units to efficiently sample compressed LLMs with hardware; turns out Apple foundation models are already doing this [1].
Without context, it should be number of params * 1.76 (the “effective bits per weight”) / 8
So for this one, 27B * 1.76 / 8 = 5.94 GB
For speed, far as I can tell it depends if your gpu is memory bandwidth bound or (mostly older gpus) processing bound. If it’s memory bandwidth bound, and your gpu gets 300GB/s, that’s:
300GB/s / 5.98 GB = 50.5t/s.
Realistically it’s probably a bit slower, but that is your theoretical maximum.
"Ternary Bonsai 2 27B reaches up to 143 tokens/second on NVIDIA GeForce RTX 5090 and 46.8 tokens/second on M5 Max. On an RTX 4090, Ternary Bonsai 2 27B consumes just 0.714 mWh/token, making it 40% more energy-efficient than an 8B model running in full-precision."
150 tokens per second on a ternary model implies that it’s GPU bound, I’d bet a Q6 model is even faster because it’s existed longer and seen more optimization. You’d have to be insane to not run an NVFP4 quant over a ternary quant on Blackwell if they both fit.
(In case anyone remembers the compression post from yesterday[1], I checked and this one doesn't qualify for further compression - it's not zero-biased at all.)
If you want to try out out the GGUFs from https://huggingface.co/prism-ml/Ternary-Bonsai-2-27B-gguf#th... be aware that you need Prism's llama.cpp fork to get them to work, from https://github.com/PrismML-Eng/llama.cpp/releases/tag/prism-...
This should work:
Then open http://localhost:8331 for the (very good) baked in llama-server web UI... or run a prompt via the API like this: That's running at ~20 token/second for me on an M5 Pro (after a server restart I got 44 token/second, not sure why), but I'm pretty sure something isn't working right, on startup the server said "ggml_metal_device_init: - the tensor API is not supported in this environment - disabling".I managed to run it with RTX 3070 (8GB VRAM) following the "Quickstart" on HF model card with minor modifications (modify the architecture 86 for your own hardware):
Then downloaded & verified `Ternary-Bonsai-2-27B-PTQ1_0.gguf` from HF and ran the parameters were suggested by gpt-5.6-luna to reduce memory footprint, as the defaults ran OOM on my gpu. result looks good: would be nice if they upstreamed their changes so that it runs with the original llama.cppI used that to Generate an SVG of a pelican riding a bicycle:
https://tools.simonwillison.net/markdown-svg-renderer?url=ht...
It took 18 minutes 20 seconds. Pretty decent for a 5.5GB model file.
How does that compare with the bf16 version?
For my "Please recite Jabberwocky" test the bf16 almost passes but the ternary and even fp8 versions fail badly.
M1 Pro, same prompt, same cli options:
Honestly looks pretty good except whatever is going on with its booty. Is that an ass helmet? I cannot parse what's going on there.
Like you've never worn an ass helmet
Only because I hadn't previously thought of it xD Step up from the standard ass-hat for sure.
I think it’s supposed to be a wing
I like the lens effect behind the rear tire.
If you want to download the gguf to your regular huggingface cache directory instead of to /tmp, you can download the model and run the server in one step:
Thanks for all of your exploration in public Simon.
Commenting because the fix I proposed was merged in roughly 49 commits after the PrismML Fork. The “tensor API is not supported” warning occurred because llama.cpp’s startup probe fails to compile a matmul2d kernel: Metal’s tensor headers require language version 4.0, but ggml-metal-device.m previously omitted MTLCompileOptions.languageVersion, disabling the API universally.
Here’s a link to the diff if you want to try and update that fork to take advantage of the prefill gains afforded by the hardware: https://github.com/ggml-org/llama.cpp/pull/27461/changes
That kind of issue is exactly why Im so happy to have LLMs, let it take one hour or trial and error instead of me spending a day digging traces
Where did you get these instructions?
They have a demo repo with a setup.sh script:
https://github.com/PrismML-Eng/Bonsai-demo
The release tag and weight file you suggest doesn’t match what they wrote.
I figured them out, starting from the GGUF on Hugging Face.
If you have found better instructions and they work then use those instead!
Personally I prefer to download models directly rather than running some `./setup.sh` script where I need to then review what it does first.
Yeah just wanted to mention in case it explains the 2x lower throughout you are seeing on M5. To be fair their documentation is a bit inconsistent in some spots.
Would be good to know if the release and weights from their demo repo work better. I’m trying on a 4090 and will report back.
It would be great to have upstream llama.cpp support for this!
Agreed. They always sound exciting to try out but are such a pain to get working.
I always just throw an agent at it. Is this the RSI I keep hearing about
RSI saves you from RSI
Let’s see, so if you get the same 1/9th the size compression ratio with GLM-5.3-Flash, then you’d end up with a ~72GB model that’s about as good as GPT-5.6 Sol (high), according to artificialanalysis.ai
Which is within reach of some higher end consumer hardware, especially with layer offloading.
You have to wonder what kind of trouble the “labs” are in when this is becoming possible. Lots of money, where’s the moat?
There's a chap called Bijian Bowen who does very quick agentic coding challenges for new models (very soon after release!) mainly for toy games or websites. He just did one for this model and included a comparison with the base model Qwen 3.8 which shows the "near-lossless" claim should be taken with a grain of salt. It is an interesting model if you are GPU starved and want local, but you might have trouble finding things it is good at.
I really wish people would stop saying N times smaller than something when making a comparison; that makes no sense - it's 1/9th (11.11%) the size. You don't get a smaller quantity by multiplying by a number greater than 1.0. You could instead reverse the subjects being compared - "the original model is 9x bigger than this new smaller, efficient model" or some such. That makes sense.
I keep seeing this being used when people talk about efficiency or performance gains and it's just very unintuitive language.
I agree it makes little sense in a literal mathematical take but "it's 9x smaller" or is too much of linguistic advantage compared to "the original is 9x larger" or "it's 1/9th as large" to expect a change with. You don't have to invoke fractions, it keeps the thing in focus as the first subject, it matches the pattern of the inverse statement, and it's just plain short... so that's what people will adapt and interpret the meaning to be.
One other way to map both types of linguistic statement consistently to math is to interpret "9x" as "there is a 9 times difference between these two things" and then "smaller"/"larger" tells you which end of that separation the subject is (rather than specifying whether the multiplication builds up or down).
"it's 11% as large" avoids fractions but is much more clear (IMO) than "9x smaller" which my brain doesn't understand.
11% is also a really saying a fraction, 11 per-cent or 11/100, but there's nothing wrong with that feeling more natural to some and it is at least a nice shorthand way for the written form. "A ninth the size" is a similar alternative. All are really fine, there's always someone who has trouble with a given representation compared to another.
If we were talking about speed instead of size, i think it would be perfectly reasonable to say 9x faster. I'm not sure I agree that 9x smaller is unintuitive. It makes sense to me.
"Nine times" literally means multiplied by nine, but here we're dividing by nine. It's not unintelligible (because the corrupted verbiage is so commonplace) but it is needlessly awkward. Like saying "resulted in a size reduction increase of 10 megabytes."
> "Nine times" literally means multiplied by nine
Rather, "nine times larger" means multiplied by nine, and "nine times smaller" means divided by nine. This is basic and not particularly awkward, certainly not more so than e.g. positive/negative correlation, or many much more awkward and more common linguistic constructions, IMO.
If you have to edit out words (i.e. context) to argue a phrase doesn't make sense... I am not sure what mental model you have for natural language, exactly, but it certainly isn't a very robust one.
"faster" relates to speed. Speed is related to time and speed of a thing is usually defined by time. 9x faster speed translates to time/9. There is an extra step of related conversion there.
Conversely, 9x [filesize/natural number] is bigger. Every time. At least in the basic maths used by most people. There is no conversion into other units.
Therefore "9x smaller" when talking about a natural number like filesize is a nonsense statement in logic terms. If you strive for unambiguous phrasing - which is a significant part of the programming experience - this logical nonsense might well perturb you.
But english language is a flexible thing and if the phrase communicates your intent to your audience then that's fine by me.
I think more intuitively for speed - you are multiplying the things per period. If I’m making widgets 9x faster I have 9 x the previous number of units per period of time. To get the amount of time, you invert the ratio to period over units.
Multiplying some scale by units per period makes sense and is both linguistically and mathematically sound.
It's simple
If 9 is "9 times greater" than 1 then 1 must be "9 times smaller" than 9
It'd help if you read "9 times" with the operator which is what's being flipped instead of with the number
This is widespread usage.
I don't see what makes it hard to understand.
Also, X is 9 times larger than Y and X is 9 times as large as Y are two different statements.
They probably rephrased it from some more technical form like "we compressed the model by a factor of 9" or "we've improved the packing efficiency of the model by 9x". Where these are measurements of the transformation the model is undergoing, not measurements of the resulting model.
But we're cutting drug prices 500, 800, 1700%! Numbers nobody thought were possible.
It was hilarious that this is the only time his, er, meta-imaginary-gains intensifier made the statement literally true.
This sounds like the same kind of error as writing "0.10 cents" because it's less than a dollar when the number is in dollars regardless of how big or small it is
Eh, when I read smaller with an integer multiplier, I mentally switch to the reciprocal. Easier than convincing the world not to use "9x smaller". Do you feel the same way about "9x faster"? What you're actually measuring is time, and "faster" is the reciprocal of time, similarly to "smaller" being the reciprocal of size.
yes, actually I do think the phrase 'N times faster' is sensible and logical
if I say 'this Apple M5 chip is 3x faster' than this intel chip, it implies two things:
- the run time of most operations that runs on it is now reduced (so one quantity is smaller)
- but also: MORE WORK is being completed per unit of time compared to the intel chip (so this quantity is greater)
So yes, a greater quantity is being measured in the apple chip compared to the intel when you say apple is N times faster. i guess this a quirk with the word 'faster' - it actually measures two things, time and work performed per unit of time. the word smaller just measures size.
like, if I give a customer a cup of coffee one day, then give them a SMALLER cup of coffee the next day, for the same price, but declare "It's now 2X more space efficient!" i.e. it's now half the size, I'm certain the customer is gonna be pissed.
Ah, but in this case the customer is buying the coffee for the caffeine content. And you've doubled the caffeine content per volume! Twice as efficient a delivery mechanism, similar to this model!
I completely agree and this is a pet peeve of mine so it's nice to be validated :]
Me too!! It's a huge pet peeve. And it's so hard to get people to see how it's linguistically AND mathematically WRONG.
I disagree completely and I'd be happy to be convinced otherwise
These are small enough that you can run them entirely in the browser https://huggingface.co/spaces/webml-community/ternary-bonsai...
Remember to clear the downloaded weights afterward.
Like the last model, it's amazing they work as well as they do. Use it for any longer task and they fall apart spectacularly and in interesting ways.
So you have some fun examples?
Sadly crashing on Pixel 9 Pro, but I guess phone GPU with 16GB RAM total wouldnt be enough anyway.
Runs on my 16GB M2 Air (firefox). ~7 tok/s
It should be though.
Even native AI gallery uses smaller Gemma models. I guess whatever Chrome is using for WebGPU compute on Android is just adding too much overhead.
Fyi, if you're trying to run this under AMD/HIP:
PTQ1_0 has no optimized MMQ-Path in their llama-cpp fork, try running PTQ2_0 (needs a bit more vram, but is about 2x faster on my 6700 XT)
https://gist.github.com/nilsherzig/b8266d001c5c01bdb3d81d209...
> Ternary Bonsai 2 27B uses ternary {−1, 0, +1} weights with FP16 group-wise scaling, for 1.76 effective bits per weight
If I recall correctly, a recent post [1] has shown that Q2 quants (with like 2.6 bpw) of the same base Qwen model sit at the edge between "noticeably worse" and Q1's "useless". I took a quick glance at Bonsai's blog posts, and don't really see them comparing themselves to "typical" quants or explaining what's the special sauce that makes them better?
https://news.ycombinator.com/item?id=49611128
There's a table on the HF page that compares it against UD-Q4_K_XL and IQ2_XXS (you need to expand the dropdown): https://huggingface.co/prism-ml/Ternary-Bonsai-2-27B-gguf#fu...
The table claims it performs on par with UD-Q4_K_XL except on OCR.
I wonder how well it performs in practice, because I can't help seriously doubting those benchmarks. That would put this 6GB model in Opus 4.6+ ballpark. Granted, that's mostly to Qwen 3.8's credit, but it's hard to believe that Qwen's already unbelievable capability density can still be compressed this much more.
I think the general idea is naive quantization falls apart below 4bpw but you can go lower with more sophisticated QAT-adjacent methods. Bonsai's quantization method is proprietary though.
That's correct. I think there can certainly be issues even with 4bpw with naive quantization (IE you'll notice far better results from a QAT 4bpw vs a naive 4bpw).
One such method that I've been meaning to look into further is Tencent's AngelSlim QAT/PTQ approach. They did a Hy4 preview release thats an STQ_1_0 at 2.38 bpw:
https://huggingface.co/AngelSlim/Hy4-preview-GGUF https://arxiv.org/abs/2602.21233
Of course, it's still 213g of VRAM I'd need so it's somewhat out of the range of what I can run locally. In contrast, this new Bonsai is nice because the original was already exciting for making use of low VRAM devices. Could breath new life into some of the older GPUs that were previously close to top of the line just quite VRAM constrained by modern standards and still quite cost effective for now.
Could've been better if GGUF implemented QTIP format. GGUF representation is a major limitation for llama.cpp quantization performance
They use their own llama fork anyway, so that shouldn't matter.
1.76 bpw number is kinda misleading if you compare it directly to IQ2/Q2. The encoding is ternary, but the quantization procedure is way more sophisticated than "round Qwen weights to {-1,0,+1}."
They rotate the weights into a quantization-friendly basis first, then ternarize with per-group scales and error compensation.
Nice! Does anyone know how this compares to the Unsloth quantizations of this model? https://unsloth.ai/docs/models/qwen3.8#run-qwen3.8-guide
Unsloth has been dethroned by ISTA:
https://huggingface.co/ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF
The 3-bit quant is lossless based on benchmarks.
There's a table on the HF page that compares it against Unsloth's UD-Q4_K_XL and IQ2_XXS: https://huggingface.co/prism-ml/Ternary-Bonsai-2-27B-gguf#fu...
Oh, wow, they think it's just a smidge below the q4? That's crazy good if true.
The benchmarks they chose are rather cherry picked to not include long context or difficult ones that involve long horizon work or many agent turns, as I suspect this is where the model shows more differences compared to the full fat one
Yep more hops from the lower Q is likely going to skew the vectors further over time.
I wonder if there's a way to mitigate this by running it through an original Q8 draft model, attuned somehow for the PTQ1 quant, but giving it a higher threshold for the acceptance linear with the context length itself?
The longer the context, the higher the multiplier on the threshold, and more likely the draft result is used. Not ideal but it may extend the usable max context.
This model might, even without this, be amazing for short lived agents that work via generations / have changing tasks.
Came to ask the same. From my really rough understanding, it seems like Unsloth's method allows a slightly higher precision at a higher file size, while PrismML's uses a different approach to achieve a smaller size (and presumably less precision).
What is never totally clear with a lot of these releases is the scope of what it's good at. Models that can run with good speed on affordable consumer hardware for coding only is the dream. I am never going to use this for writing, images, or "general knowledge". Coding only
Running at about 7-8 tok/s (~60 tok/s prefill) on a Mac Mini M2 16GB.
So far feels smarter than Bonsai 1 27B, it’s slightly larger than the Q1_0 quant. Super exciting stuff :)
Love this for the folks with 16gb graphics cards - 3.8 27b has been incredible but not quite runnable on anything less than 32gb - will try loading this up on my 16gb intel b50 and see how it goes - not sure these quants can be accelerated by the XPU cores yet but maybe in time!
I run qwen 27b on an old-ass 16gb gpu. It’s very possible using unsloth 2bit and 3bit quants, tho there are a bunch of interesting quants that let you run closer to 4bit on 16gb. This article that’s currently also on the front page mentions a bunch of them while discussing their own quant https://byteshape.com/blogs/Qwen3.8-27B/
You can run the ~4 bit quant(s) on 24gb, if you're not _too_ picky on context size.
This will hopefully be better, though it'd be a _very_ surprising increase in performace at the size they say. Would love to see more about how it benchmarks.
I run Unsloth's UD-Q4_K_S on 20 GB of VRAM (RX 7900 XT) and I get ~90k tokens of context without quantizing KV cache. With 8-bit quantization, I get about a 134k token context window. That's with only one slot, but for me, it works pretty darn well, with 20-35 tok/s depending on how full that window is.
7900 XT is a sleeper card. When I initially bought it, it was priced at the lowest wattage per $ per GB VRAM (not normalized for token speeds...) Although I ended up swapping for the XTX because that 4GB means everything in just increasing the context window. At 8bit KV my window is over 200k, and although qwen3.8 loves vomiting out tokens as part of its reasoning chain I trust it enough to get assigned tasks done eventually, which I could not say of any model before its release.
How has software/driver support been? I got burned hard by AMD last generation or the one before. Things smoother now, or do you have to baby it like hell and pick and choose software that works?
I don't do anything fancier than inference, and I only use llama.cpp, which supports rOCM. I've had few issues; most GGUFs I download work right out of the box. Nearly any popular model has a quant that just works. But as you can see I don't use my GPU for anything weird or nonstandard.
You can trivially run 131k on 24GB 4bit, and there are repos with tweaks that allow you to get the full 262k but idk if there's degradation with their approach.
I'm doing the same with a context of about 128-150k Surprisingly, I get subjectively better results with Unsloth's 3 bit quants (UD-Q3-XL something), than their 4 bit quants (S or M)
Tried it today on a B70 and couldn't get anything usable out of it.
Prism's llama.cpp fork only has the kernels for CUDA, CPU and Vulkan. No SYCL at all :(
They need to make a Big Bonsai, something at the enterprise levels that can compete with DSV4 Flash etc.
A Tree if you will
Or Grove
I'm hoping they release an 8B v2 based on the Qwen 3.8 series in the near future - that would give us a really powerful model that could be run directly on users phones.
That would require Alibaba releasing a Qwen 3.8 8B first
Yes! And maybe get a hf fused webgpu runner for that model so it’s fast!
Testing on a MBP m4 pro 24gb
~100t/s prefill, ~15t/s, dropping to ~10t/s later with 64k context.
The issue is I have yet to find a useful agentic local llm that I can run on this machine.
Just given a relatively simple task on a swift app, took 25 minutes, brainstorming like crazy but can not decide on what to do. Eventually I killed it. GPT 5.6 sol-medium took 3 minutes to complete the same task for reference.
Gemma 30B with 256K context runs at 20 tok/sec on my M3 Max with 128GB RAM so I think there’s something wrong with your setup. This should run at ~30-40 toks. Maybe your inference engine is not optimised for Mac.
I just used their `Bonsai-demo` repo like this;
`cd ~/Code/Bonsai-demo && BONSAI_CTX=65536 ./scripts/start_llama_server.sh`
then used it in a very minimalistic pi with a very small system prompt.
Didn't spend much time to try to optimize it tbh, but my issue was not the speed. it just could not make a decision on how to implement the task, kept going on an on.
30B is useless on 24 gigs of ram as there's ~4 gigs of ram left for everything else even with unsloth quants
Try a MoE model like Qwen3.6 35B-A3B for better tok/s
I tried this one, but I found Ornith1.5 to be a better MoE model for me, also very fast. But I still couldn't make it implement a real task on a real repo :( it only worked with an extremely clear directions and very small tasks.
I tried their WebGPU version and it immediately started looping. Yeah "near lossless" my ass. Plus the reasoning that it looped on was clearly wrong and unlike the non quantized 27B
Hello! May I ask, is this model compatible with my RX 9070 on Linux?
The dev didn’t list AMD Radeon support, and I couldn’t get it to work
I wonder how their talks with Apple went. Having this run on the TPU opposed to just the GPU, which drains a significant amount of battery life by comparison, is what I'm really interested in.
Cautiously optimistic. The V1 was noticeably weak on world knowledge but here the 3.8 base model is geared more towards reasoning than world knowledge anyway so might not matter as much
I think if they made this for Qwen3.8-Next it could fit in a single 5090?
180b * 1.76 bits per weight = 39.6 gigabytes.
Best you could realistically run in 32gb is like 28gb, or a 127B param model
Qwen3.8-Next, thanks to its new architecture, is quite fast even if part of it is streaming from disk
GPT Astra did some benchmarking on the DGX Spark. Speed: 34.38 tokens/sec for generation.
Seems like we don't have a drafter model yet so it could not test with speculative decoding on. ngram speculative decoding did not help too much either - not enough accepted tokens.
Smaller size I suppose does not mean better performance in this case - we maybe limited by Spark's low memory bandwidth.
That's a rough place to land on a spark. It seems unlikely to be memory bandwidth at this model size, but maybe just lack of tuned kernels? The chip is missing some CUDA features but with tuning you should be able to hit way more than that even without a drafter.
I was wondering if those ternary bits get expanded into full floats internally in the kernels - you’re probably right about lack of tuned kernels. I’m not sure you could just tune your way out of that easily though. Any suggestions on trying particular solutions?
What are you getting for prefill?
450 with PTQ_01 and 900 with the other PQ2_0.
Never heard of Bonsai before, but that looks great and promising for local on-device inference.
Yet, seems like there is still another year for improvements.
I like local models (but not mainly using them) for offline needs.
LLM quants seem to eerily converge to modern/not so modern graphics techniques. You wouldn't think it would apply but it's obvious in hindsight. In fact mining graphics ideas is probably a good inspiration for efficient LLM architecture.
For example, the Hadamard activation transform used here feels a lot like multiplying Fourier basis ala DFT; strong parallels to how image codecs work to make the residuals more compressible (especially discrete block codecs like are used in GPU compressed textures).
I thought I was being clever suggesting that you could even abuse texture decode units to efficiently sample compressed LLMs with hardware; turns out Apple foundation models are already doing this [1].
[1] https://arxiv.org/abs/2507.13575
What I'd love to see is this done for DS4.1 Flash.
That would bring it down to the point where it can fit in 128GB on things like the Spark or Strix Halo.
I'd love to see a Bonsai model start with a 100B+ parameter model and get that down to <30 GB. But maybe at that point we call it Topiary?
Other names that occur to me: Orchard, Forest, Stand (of trees).
Bonsai Dai ?
I tried it on my 6GB GPU and got 0.67 tokens per second. Need more than 6GB to run it well.
Is it just me or are local models getting better (catching up) a lot faster than the frontier models are getting better (creating distance)?
If true, that would be a very welcome development.
RAM requirements? My current rule of thumb is “a byte per parameter”, but I doubt this runs in 1/9th that (~ 3GiB).
Also, perf speedup?
Without context, it should be number of params * 1.76 (the “effective bits per weight”) / 8
So for this one, 27B * 1.76 / 8 = 5.94 GB
For speed, far as I can tell it depends if your gpu is memory bandwidth bound or (mostly older gpus) processing bound. If it’s memory bandwidth bound, and your gpu gets 300GB/s, that’s:
300GB/s / 5.98 GB = 50.5t/s.
Realistically it’s probably a bit slower, but that is your theoretical maximum.
I'm seeing around 7.9GB of ram, 120 tokens/s on a 6000 pro blackwell.
Awesome results. Opens up doors for a lot of people.
I'm not following the local mdoel scene too closely but this seems quite amazing. Is this able to be run on Apple silicon too?
Their first 27B bonsai was able to run on an iphone.
"Ternary Bonsai 2 27B reaches up to 143 tokens/second on NVIDIA GeForce RTX 5090 and 46.8 tokens/second on M5 Max. On an RTX 4090, Ternary Bonsai 2 27B consumes just 0.714 mWh/token, making it 40% more energy-efficient than an 8B model running in full-precision."
Their mention of the 5090 is bit odd, since on 32 GB GPUs, Q6 fits while having better quality. Very interesting model for 16 GB GPUs though!
Sometimes you want a decent model running in the background that doesn't take up all the VRAM.
Or maybe even to run parallel threads of the same model!
They mention 5090 with regards to speed, Q6 will not have that speed?
And speed matters a lot for many use cases
150 tokens per second on a ternary model implies that it’s GPU bound, I’d bet a Q6 model is even faster because it’s existed longer and seen more optimization. You’d have to be insane to not run an NVFP4 quant over a ternary quant on Blackwell if they both fit.
With Ninfer and Qwen 3.8 27b it uses a groupwise int mixed quant, and it gets 160 tokens/sec. The mixed quant is between 4 and 6 bits.
it is like "my fridge is 2mkm (millikilometer) from my desk" m=0.001 h=3600 it should be just Ws or just J
What’s wrong with milliwatt hours?
https://xkcd.com/2946/
https://xkcd.com/3038/
(In case anyone remembers the compression post from yesterday[1], I checked and this one doesn't qualify for further compression - it's not zero-biased at all.)
[1] https://news.ycombinator.com/item?id=49732931