6-bit Open on Hugging Face
Parameters
32B
Weights (est.)
≈ 25.7 GB
Mac memory (est.)
32 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/OpenResearcher-30B-A3B-6bit --prompt "Hello"
Details
- Base model
- OpenResearcher/OpenResearcher-30B-A3B (quantized)
- Vendor
- OpenResearcher
- Task
- Text generation
- Quantisation
- 6-bit
- Licence
- mit
- Downloads
- 96 in the last 30 days · 470 all time · 0 likes
- Published
- 2026-02-10 · updated 2026-02-10 (9mo ago)
- Tags
- nemotron_h, custom_code