3-bit Open on Hugging Face
Parameters
46B
Weights (est.)
≈ 20.2 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/Klear-46B-A2.5B-Instruct-3bit --prompt "Hello"
Details
- Base model
- Kwai-Klear/Klear-46B-A2.5B-Instruct (quantized)
- Vendor
- Kwai-Klear
- Task
- Text generation
- Quantisation
- 3-bit
- Licence
- apache-2.0
- Downloads
- 32 in the last 30 days · 344 all time · 0 likes
- Published
- 2025-09-08 · updated 2025-09-08 (1y ago)
- Languages
- zh, en
- Tags
- Klear, custom_code