Google · First MLX build 29 Jun 2025 · In Core AI since 3 Sept 2026
gemma-3n-E2B-it
MLXCore AI
Text gemma
A 5.4B parameter text generation model from Google, with 3 MLX builds, from 4-bit to bf16 and Apple Core AI export recipes for macOS.
- Parameters
- 5.4B From Hugging Face
- Quantisation
- 4-bit gemma-3n-E2B-it-lm-4bit
- Memory needed
- 5 GB Estimate, unified memory
- Download
- 2.5 GB Weights, estimated
- Downloads
- 2.5K This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 3 On mlx-community
- Devices
- Mac Apple silicon
- Parameters
- 5.4B From Hugging Face
- Compression
- 4-bit Apple’s preset
- Memory needed
- 6 GB Estimate from parameters
- Context
- 32K tokens Fixed at export
- Precision
- FP16 Compute precision
- Platforms
- macOS Mac
- Export presets
- 1 In Apple’s registry
- Listed by Apple
- 3 Sept 2026 First registry commit
Memory
Will it fit?Needs about 5 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-3n-E2B-it-lm-4bit --prompt "Hello"Memory
Will it fit?Needs about 6 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 gemma-3n-e2b-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
3 on mlx-community| gemma-3n-E2B-it-lm-4bit | 4-bit | 2.5 GB | 5 GB | 2.5K |
|---|---|---|---|---|
| gemma-3n-E2B-it-text-4bit-dwq | 4-bit DWQ | 5.2 GB | 8 GB | 150 |
| gemma-3n-E2B-it-lm-bf16 | bf16 | 8.9 GB | 12 GB | 71 |
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 |
|---|---|---|---|---|
| gemma-3n-e2b-it | macOS | 4-bit | FP16 | 32K |