4-bit Open on Hugging Face
Parameters
123B
Weights (est.)
≈ 69.0 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/magnum-v4-123b-4bit --prompt "Hello"
Details
- Base model
- anthracite-org/magnum-v4-123b (quantized)
- Vendor
- anthracite-org
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- mrl
- Downloads
- 69 in the last 30 days · 752 all time · 0 likes
- Published
- 2024-12-18 · updated 2024-12-18 (1y ago)
- Languages
- en
- Tags
- mistral, chat