Google · First MLX build 14 May 2025 · In Core AI since 8 Jun 2026
gemma-3-12b-it
MLXCore AI
Text gemma
A 12B parameter text generation model from Google, with one MLX build at 4-bit DWQ and Apple Core AI export recipes for macOS.
- Parameters
- 12B From Hugging Face
- Quantisation
- 4-bit DWQ gemma-3-12b-it-4bit-DWQ
- Memory needed
- 11 GB Estimate, unified memory
- Download
- 7.2 GB Weights, estimated
- Downloads
- 90 This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 1 On mlx-community
- Devices
- Mac Apple silicon
- Parameters
- 12B From Hugging Face
- Compression
- 4-bit Apple’s preset
- Memory needed
- 10 GB Estimate from parameters
- Context
- 128K tokens Fixed at export
- Precision
- BF16 Compute precision
- Platforms
- macOS Mac
- Export presets
- 1 In Apple’s registry
- Listed by Apple
- 8 Jun 2026 First registry commit
Memory
Will it fit?Needs about 11 GB at 4-bit DWQ
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-3-12b-it-4bit-DWQ --prompt "Hello"Memory
Will it fit?Needs about 10 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 parameter count at Apple’s compression setting. Apple does not publish package sizes.
Export it
Terminal · uv$ git clone https://github.com/apple/coreai-models
$ cd coreai-models
$ uv run coreai.llm.export gemma3-12b-it
Apple publishes the recipe, not a ready-made package: these commands convert the original weights to a Core AI .aimodel on your Mac. See the repository for requirements.
MLX builds
1 on mlx-community| gemma-3-12b-it-4bit-DWQ | 4-bit DWQ | 7.2 GB | 11 GB | 90 |
|---|
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.
Core AI export presets
From Apple’s registry| Preset | Platform | Compression | Precision | Context |
|---|---|---|---|---|
| gemma3-12b-it | macOS | 4-bit | BF16 | 128K |