8-bit Open on Hugging Face
Parameters
1.5B
Weights (est.)
≈ 1.6 GB
Mac memory (est.)
8 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/Arch-Router-1.5B-mlx-8Bit --prompt "Hello"
Details
- Base model
- katanemo/Arch-Router-1.5B (quantized)
- Vendor
- katanemo
- Task
- Text generation
- Quantisation
- 8-bit
- Licence
- katanemo-research
- Downloads
- 1.2K in the last 30 days · 1.8K all time · 0 likes
- Published
- 2025-10-17 · updated 2025-10-17 (1y ago)
- Languages
- en
- Tags
- qwen2, routing, preference, mlx-my-repo