8-bit Open on Hugging Face
Parameters
8.5B
Weights (est.)
≈ 9.1 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/codegemma-1.1-7b-it-8bit --prompt "Hello"
Details
- Base model
- google/codegemma-1.1-7b-it (finetune)
- Vendor
- Google · Gemma
- Task
- Text generation
- Quantisation
- 8-bit
- Licence
- gemma
- Downloads
- 80 in the last 30 days · 1.6K all time · 2 likes
- Published
- 2024-05-03 · updated 2025-06-02 (1y ago)
- Tags
- gemma
Other MLX builds of google/codegemma-1.1-7b-it
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| codegemma-1.1-7b-it-6bit | 6-bit | ≈ 6.9 GB | 16 GB+ | 55 |
| codegemma-1.1-7b-it-8bit (this one) | 8-bit | ≈ 9.1 GB | 16 GB+ | 80 |