4-bit Open on Hugging Face
Parameters
27B
Weights (est.)
≈ 15.3 GB
Mac memory (est.)
24 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-2-27b-it-bf16-4bit --prompt "Hello"
Details
- Base model
- google/gemma-2-27b-it (quantized)
- Vendor
- Google · Gemma
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- gemma
- Downloads
- 85 in the last 30 days · 712 all time · 0 likes
- Published
- 2024-10-22 · updated 2024-11-06 (2y ago)
- Tags
- gemma2
Other MLX builds of google/gemma-2-27b-it
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| gemma-2-27b-it-bf16-4bit (this one) | 4-bit | ≈ 15.3 GB | 24 GB+ | 85 |
| gemma-2-27b-it-bf16-8bit | 8-bit | ≈ 28.9 GB | 48 GB+ | 64 |