3-bit Open on Hugging Face
Parameters
389B
Weights (est.)
≈ 170 GB
Mac memory (est.)
256 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/Hunyuan-A52B-Instruct-3bit --prompt "Hello"
Details
- Base model
- tencent-community/Hunyuan-A52B-Instruct (quantized)
- Vendor
- tencent-community
- Task
- Text generation
- Quantisation
- 3-bit
- Licence
- —
- Downloads
- 67 in the last 30 days · 3.6K all time · 5 likes
- Published
- 2024-11-23 · updated 2024-11-23 (1y ago)
- Languages
- en
- Tags
- hunyuan, custom_code