MLX Community · First MLX build 5 Jun 2026
gemma-4-12B-it-qat-assistant
MLX
Text gemma
A 423M parameter text generation model, with 8 MLX builds, from 4-bit to bf16.
- Parameters
- 423M From Hugging Face
- Quantisation
- 4-bit gemma-4-12B-it-qat-assistant-4bit
- Memory needed
- 3 GB Estimate, unified memory
- Download
- 238 MB Weights, estimated
- Downloads
- 466 This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 8 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 3 GB at 4-bit
8 GB
16 GB
24 GB
32 GB
64 GB
128 GB
Fits with headroomTight, close other appsWon’t fit
Estimated from the size of the weights, plus a fifth for context and working memory and 2 GB for macOS and your apps. Long contexts need more.
Run it
Terminal · mlx-lm$ pip install -U mlx-lm
$ mlx_lm.generate --model mlx-community/gemma-4-12B-it-qat-assistant-4bit --prompt "Hello"MLX builds
8 on mlx-community| gemma-4-12B-it-qat-assistant-4bit | 4-bit | 238 MB | 3 GB | 466 |
|---|---|---|---|---|
| gemma-4-12B-it-qat-assistant-mxfp4 | MXFP4 | 238 MB | 3 GB | 58 |
| gemma-4-12B-it-qat-assistant-nvfp4 | 4-bit | 238 MB | 3 GB | 50 |
| gemma-4-12B-it-qat-assistant-5bit | 5-bit | 291 MB | 3 GB | 57 |
| gemma-4-12B-it-qat-assistant-6bit | 6-bit | 344 MB | 3 GB | 54 |
| gemma-4-12B-it-qat-assistant-8bit | 8-bit | 449 MB | 3 GB | 123 |
| gemma-4-12B-it-qat-assistant-mxfp8 | MXFP8 | 449 MB | 3 GB | 44 |
| gemma-4-12B-it-qat-assistant-bf16 | bf16 | 846 MB | 3 GB | 90 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.