4-bit Open on Hugging Face
Parameters
111B
Weights (est.)
≈ 62.5 GB
Mac memory (est.)
96 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/Agatha-111B-v1-4bit --prompt "Hello"
Details
- Base model
- TheDrummer/Agatha-111B-v1 (quantized)
- Vendor
- TheDrummer
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- —
- Downloads
- 30 in the last 30 days · 268 all time · 0 likes
- Published
- 2025-06-12 · updated 2025-06-12 (1y ago)
- Tags
- cohere2
Other MLX builds of TheDrummer/Agatha-111B-v1
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Agatha-111B-v1-4bit (this one) | 4-bit | ≈ 62.5 GB | 96 GB+ | 30 |
| Agatha-111B-v1-8bit | 8-bit | ≈ 118 GB | 192 GB+ | 25 |