bf16 Open on Hugging Face
Parameters
4.5B
Weights (est.)
≈ 8.9 GB
Mac memory (est.)
16 GB+
Size is estimated from the parameter count and quantisation. Memory allows a fifth extra for context plus 2 GB for the system; long contexts need more.
Run it
With mlx-lm on an Apple silicon Mac:
pip install mlx-lmmlx_lm.generate --model mlx-community/gemma-3n-E2B-it-lm-bf16 --prompt "Hello"
Details
- Base model
- google/gemma-3n-E2B-it (finetune)
- Vendor
- Google · Gemma
- Task
- Text generation
- Quantisation
- bf16
- Licence
- gemma
- Downloads
- 73 in the last 30 days · 2.0K all time · 0 likes
- Published
- 2025-06-29 · updated 2025-06-29 (1y ago)
- Tags
- gemma3n, automatic-speech-recognition, automatic-speech-translation, audio-text-to-text, video-text-to-text
Other MLX builds of google/gemma-3n-E2B-it
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| gemma-3n-E2B-it-lm-4bit | 4-bit | ≈ 2.5 GB | 8 GB+ | 2.5K |
| gemma-3n-E2B-it-text-4bit-dwq | 4-bit DWQ | ≈ 5.2 GB | 8 GB+ | 137 |
| gemma-3n-E2B-it-lm-bf16 (this one) | bf16 | ≈ 8.9 GB | 16 GB+ | 73 |