8-bit Open on Hugging Face
Parameters
2.6B
Weights (est.)
≈ 2.8 GB
Mac memory (est.)
8 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-2-baku-2b-it-8bit --prompt "Hello"
Details
- Base model
- google/gemma-2-2b (merge)
- Vendor
- Google · Gemma
- Task
- Text generation
- Quantisation
- 8-bit
- Licence
- gemma
- Downloads
- 35 in the last 30 days · 393 all time · 0 likes
- Published
- 2024-10-04 · updated 2024-10-04 (2y ago)
- Languages
- ja, en
- Tags
- gemma2
Other MLX builds of google/gemma-2-2b
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| gemma-2-baku-2b-it-4bit | 4-bit | ≈ 1.5 GB | 8 GB+ | 43 |
| dolphin-2.9.4-gemma2-2b-4bit | 4-bit | ≈ 1.5 GB | 8 GB+ | 35 |
| gemma-2-baku-2b-it-8bit (this one) | 8-bit | ≈ 2.8 GB | 8 GB+ | 35 |
| gemma-2-baku-2b-it | — | ≈ 5.2 GB | 8 GB+ | 32 |
| dolphin-2.9.4-gemma2-2b-mlx | — | ≈ 5.2 GB | 8 GB+ | 24 |