Google · First MLX build 3 Jun 2026
gemma-4-12B-it-assistant
MLX
TextVisionAudio apache-2.0
A 423M parameter any to any model from Google, with 8 MLX builds, from 4-bit to bf16.
- Parameters
- 423M From Hugging Face
- Quantisation
- bf16 gemma-4-12B-it-assistant-bf16
- Memory needed
- 3 GB Estimate, unified memory
- Download
- 846 MB Weights, estimated
- Downloads
- 705 This build, last 30 days
- Task
- Any to any Text, Vision, Audio
- MLX builds
- 8 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 3 GB at bf16
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 · Hugging Face CLI$ pip install -U huggingface_hub
$ hf download mlx-community/gemma-4-12B-it-assistant-bf16MLX builds
8 on mlx-community| gemma-4-12B-it-assistant-4bit | 4-bit | 238 MB | 3 GB | 205 |
|---|---|---|---|---|
| gemma-4-12B-it-assistant-nvfp4 | 4-bit | 238 MB | 3 GB | 56 |
| gemma-4-12B-it-assistant-mxfp4 | MXFP4 | 238 MB | 3 GB | 49 |
| gemma-4-12B-it-assistant-5bit | 5-bit | 291 MB | 3 GB | 35 |
| gemma-4-12B-it-assistant-6bit | 6-bit | 344 MB | 3 GB | 46 |
| gemma-4-12B-it-assistant-8bit | 8-bit | 449 MB | 3 GB | 78 |
| gemma-4-12B-it-assistant-mxfp8 | MXFP8 | 449 MB | 3 GB | 42 |
| gemma-4-12B-it-assistant-bf16 | bf16 | 846 MB | 3 GB | 705 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.