4-bit DWQ Open on Hugging Face
Parameters
28B
Weights (est.)
≈ 16.0 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-3-27b-it-4bit-DWQ --prompt "Hello"
Details
- Base model
- google/gemma-3-27b-it (quantized)
- Vendor
- Google · Gemma
- Task
- Text generation
- Quantisation
- 4-bit DWQ
- Licence
- gemma
- Downloads
- 53 in the last 30 days · 7.6K all time · 3 likes
- Published
- 2025-05-14 · updated 2025-05-14 (1y ago)
- Tags
- gemma3
Other MLX builds of google/gemma-3-27b-it
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Gemma-SEA-LION-v4-27B-IT-mlx-4bit | 4-bit | ≈ 5.3 GB | 8 GB+ | 24 |
| gemma-3-27b-it-4bit-DWQ (this one) | 4-bit DWQ | ≈ 16.0 GB | 24 GB+ | 53 |
| gemma-3-27b-it-qat-bf16 | bf16 | — | — | 40 |