I just ran one of these locally on a Mac like this:
uvx litert-lm run \
--from-huggingface-repo=litert-community/gemma-4-E2B-it-litert-lm \
gemma-4-E2B-it.litertlm \
--backend=gpu \
--prompt="Generate an SVG of a pelican riding a bicycle"
The first time you run that it downloads 3.2GB to ~/.cache/huggingface/hub/models--litert-community--gemma-4-E2B-it-litert-lm
It can handle audio and image input too, which is pretty cool for a 3.2GB model. For images:
Unsloth's collection as well [0], with their results [1]. Looks like they can get very close to 100% accuracy compared to the BF16 model that is unquantized, and Unsloth's quants are better than the original Google's QAT as posted in the article.
Personal I'm using the 2B model for web search and structured JSON output back via Unsloth Studio and its API, works very well for that even with the model embedded on phones.
you misunderstand what that chart shows - it shows BF16 QAT Q4_0, not BF16 regular.
meaning Google quantized the model to 4 bit and stored the result in BF16 format for compatibility and convenience to downstream packers.
Like storing small 8 bit numbers in full 32 bit integers.
So it's not close to 100% of unquantized BF16.
I'm curious if anybody can explain why Google released 4 bit QAT Q4_0 is not exactly 100% of BF16 QAT Q4_0? seems like it should be just bit twiddling, no further quantization to convert between these two packings. Unsloth talks about "lattice alignment" being an issue.
That being said I hate it that smol model makers, like Google, Qwen, ... only show the BF16 benchmarks when they release a new models, knowing that what people really run are 4-8 bit quantizations, so it's really hard to understand how much you lose when you run 4 bit vs 6 bit...
> meaning Google quantized the model to 4 bit and stored the result in BF16 format for compatibility and convenience to downstream packers.
You also misunderstand what is happening. Google did not do that. Google further trained the original model with an objective of minimizing error when quantized to 4-bit. The BF16 QAT is not an upscaled 4-bit model. When quantized to 4-bit, it should lose less accuracy than a typical 16-bit model loses when quantized to 4-bit, but the loss is not zero, because it is not based on a 4-bit model.
"Instead of just quantizing the model after it's fully trained, QAT incorporates the quantization process during training. QAT simulates low-precision operations during training to allow quantization with less degradation afterwards for smaller, faster models while maintaining accuracy. Diving deeper, we applied QAT on ~5,000 steps using probabilities from the non-quantized checkpoint as targets. We reduce the perplexity drop by 54% (using llama.cpp perplexity evaluation) when quantizing down to Q4_0."
The BF16 is just trained to be more resistant to simulated quantization, which helps when it is actually quantized. Google is not doing post-training on the 4-bit model directly.
It's good that this post lists the expected VRAM usage for the models with Q4_0 Gemma 4 12B being 6.7GB, which will indeed fit Google's claims of fitting within 16GB comfortably, altough it confirms that only the quantized version will do so.
Relatedly, in Google's newly released Edge Gallery for macOS, Gemma 4 12B is explicitly listed as unsupported due to not enough RAM even on a 16GB machine, but given the expected VRAM usage here the Q4_0 variant definitely should fit and Google should fix that.
I'm not sure why you think it's awkward to have multiple releases. It's better to release models and variations as they're ready, not withhold them all until everything is ready to release all at once.
The Q4_0 is a quantization aware training checkpoint. It's not a simple quantization of the original Gemma 4 12B.
It probably sounds silly and really whiny in the abstract. It just causes a ton of work / confusion downstream that feels unnecessary.
Extremely glad for the output, not glad to have to chase it.
ex. llama.cpp currently supports the originals but not the MTP predictors but there is a patch for the MTP predictors but not for the small MoE models and I think it supports the 12B but maybe not media for it yet and now we have these too and the blog says there's GGUFs (llama.cpp models) but there isn't in any of the 12? repos I clicked through. and ~every consumer-facing local LLM app is built on llama.cpp or a fork of it.
Also if anyone at Google is taking feedback over to b/ or product, pleaseeee stop the "E"2B "E"4B thing, unless it's actually taking up less RAM on Android during CPU inference. I can't tell if I need to treat the 4B like an 8B (i.e. beyond most consumer hardware without a GPU) or a 4B (i.e. will run on most consumer hardware since 2021)
EDIT: And, yes, the QAT 12B x mmproj does not work with llama.cpp. I'm glad there's people who have the luxury of not having to, well, actually use these and treat me as whining :) I'll need to schedule another 4-8 hours of work for the 4th time, no fun!
These models aren't products? They are open source ish (open weight I guess), research outputs. While the naming scheme may be confusing, it is relevant and important. I believe it's on you to understand it.
And you're absolutely right to point out they aren't products - I hoped that was clear - when you're building a product with them, you end up having to do the same build loop 4 times, in this instance :)
You can stop after the first one. Choosing to repeat the process is on you, and probably because you see some benefit in using the variant(s) you build on top of.
I was just testing Gemma E2B and E4B yesterday, and they are just too dumb to be useful outside of niche use cases.
Besides, there's no good agent on Android. Having a model that can't run web searches and browse websites is limited in use, particularly small models that really need to be grounded on search results to be factual, because they can't memorize enough.
Edit: I'd like to know what kind of usage the people that seem to disagree and downvoted this are having.
It can handle audio and image input too, which is pretty cool for a 3.2GB model. For images:
And for audio: (The pelican is rubbish, but it's only a 3.2GB file so the fact it even outputs valid SVG is impressive to me: https://gist.github.com/simonw/94b318afde4b1ce5ff67d4b5d0362... )Personal I'm using the 2B model for web search and structured JSON output back via Unsloth Studio and its API, works very well for that even with the model embedded on phones.
[0] https://huggingface.co/collections/unsloth/gemma-4-qat
[1] https://unsloth.ai/docs/models/gemma-4/qat#qat-analysis
meaning Google quantized the model to 4 bit and stored the result in BF16 format for compatibility and convenience to downstream packers.
Like storing small 8 bit numbers in full 32 bit integers.
So it's not close to 100% of unquantized BF16.
I'm curious if anybody can explain why Google released 4 bit QAT Q4_0 is not exactly 100% of BF16 QAT Q4_0? seems like it should be just bit twiddling, no further quantization to convert between these two packings. Unsloth talks about "lattice alignment" being an issue.
That being said I hate it that smol model makers, like Google, Qwen, ... only show the BF16 benchmarks when they release a new models, knowing that what people really run are 4-8 bit quantizations, so it's really hard to understand how much you lose when you run 4 bit vs 6 bit...
You also misunderstand what is happening. Google did not do that. Google further trained the original model with an objective of minimizing error when quantized to 4-bit. The BF16 QAT is not an upscaled 4-bit model. When quantized to 4-bit, it should lose less accuracy than a typical 16-bit model loses when quantized to 4-bit, but the loss is not zero, because it is not based on a 4-bit model.
https://developers.googleblog.com/en/gemma-3-quantized-aware...
"Instead of just quantizing the model after it's fully trained, QAT incorporates the quantization process during training. QAT simulates low-precision operations during training to allow quantization with less degradation afterwards for smaller, faster models while maintaining accuracy. Diving deeper, we applied QAT on ~5,000 steps using probabilities from the non-quantized checkpoint as targets. We reduce the perplexity drop by 54% (using llama.cpp perplexity evaluation) when quantizing down to Q4_0."
The BF16 is just trained to be more resistant to simulated quantization, which helps when it is actually quantized. Google is not doing post-training on the 4-bit model directly.
It's good that this post lists the expected VRAM usage for the models with Q4_0 Gemma 4 12B being 6.7GB, which will indeed fit Google's claims of fitting within 16GB comfortably, altough it confirms that only the quantized version will do so.
Relatedly, in Google's newly released Edge Gallery for macOS, Gemma 4 12B is explicitly listed as unsupported due to not enough RAM even on a 16GB machine, but given the expected VRAM usage here the Q4_0 variant definitely should fit and Google should fix that.
The Q4_0 is a quantization aware training checkpoint. It's not a simple quantization of the original Gemma 4 12B.
- Gemma 4 2B/4B/27BE3B/31B
- Gemma 4 2B/4B/27BE3B/31B x "assistant" / MTP drafter models (i.e. multitoken prediction)
- Gemma 4 12B (2 days ago? 1?)
- Gemma 4 QAT 2B/4B/12B/27BE3B/31B x "assistant" models (i.e. multitoken prediction)
It probably sounds silly and really whiny in the abstract. It just causes a ton of work / confusion downstream that feels unnecessary.
Extremely glad for the output, not glad to have to chase it.
ex. llama.cpp currently supports the originals but not the MTP predictors but there is a patch for the MTP predictors but not for the small MoE models and I think it supports the 12B but maybe not media for it yet and now we have these too and the blog says there's GGUFs (llama.cpp models) but there isn't in any of the 12? repos I clicked through. and ~every consumer-facing local LLM app is built on llama.cpp or a fork of it.
Also if anyone at Google is taking feedback over to b/ or product, pleaseeee stop the "E"2B "E"4B thing, unless it's actually taking up less RAM on Android during CPU inference. I can't tell if I need to treat the 4B like an 8B (i.e. beyond most consumer hardware without a GPU) or a 4B (i.e. will run on most consumer hardware since 2021)
EDIT: And, yes, the QAT 12B x mmproj does not work with llama.cpp. I'm glad there's people who have the luxury of not having to, well, actually use these and treat me as whining :) I'll need to schedule another 4-8 hours of work for the 4th time, no fun!
And you're absolutely right to point out they aren't products - I hoped that was clear - when you're building a product with them, you end up having to do the same build loop 4 times, in this instance :)
https://huggingface.co/google/gemma-4-26B-A4B-it-qat-q4_0-un...
(Pardon my ignorance; this stuff moves so fast)
The E4B model doesn’t fit on my phone TPU, so it swaps to RAM, the QAT version means more accuracy, good!
Besides, there's no good agent on Android. Having a model that can't run web searches and browse websites is limited in use, particularly small models that really need to be grounded on search results to be factual, because they can't memorize enough.
Edit: I'd like to know what kind of usage the people that seem to disagree and downvoted this are having.