4-bit DWQ Open on Hugging Face
Parameters
71B
Weights (est.)
≈ 39.7 GB
Mac memory (est.)
48 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/Llama-3.3-70B-Instruct-4bit-DWQ --prompt "Hello"
Details
- Base model
- mlx-community/Llama-3.3-70B-Instruct-bf16 (quantized)
- Vendor
- —
- Task
- Text generation
- Quantisation
- 4-bit DWQ
- Licence
- llama3.3
- Downloads
- 249 in the last 30 days · 8.6K all time · 5 likes
- Published
- 2025-05-23 · updated 2025-05-23 (1y ago)
- Languages
- en, fr, it, pt, hi, es, th, de
- Tags
- llama, facebook, meta, pytorch, llama-3