Hunyuan-A13B-Instruct-mixed-6-8bit
mlx-community/Hunyuan-A13B-Instruct-mixed-6-8bit
Text generation · mlx
8-bit Open on Hugging Face
Parameters
80B
Weights (est.)
≈ 85.4 GB
Mac memory (est.)
128 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-A13B-Instruct-mixed-6-8bit --prompt "Hello"
Details
- Base model
- tencent/Hunyuan-A13B-Instruct (quantized)
- Vendor
- tencent
- Task
- Text generation
- Quantisation
- 8-bit
- Licence
- tencent-hunyuan-a13b
- Downloads
- 36 in the last 30 days · 433 all time · 0 likes
- Published
- 2025-07-12 · updated 2025-07-12 (1y ago)
- Tags
- hunyuan, custom_code
Other MLX builds of tencent/Hunyuan-A13B-Instruct
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Hunyuan-A13B-Instruct-4bit | 4-bit | ≈ 45.2 GB | 64 GB+ | 107 |
| Hunyuan-A13B-Instruct-4bit-DWQ | 4-bit DWQ | ≈ 45.2 GB | 64 GB+ | 28 |
| Hunyuan-A13B-Instruct-5bit | 5-bit | ≈ 55.3 GB | 64 GB+ | 33 |
| Hunyuan-A13B-Instruct-mixed-6-8bit (this one) | 8-bit | ≈ 85.4 GB | 128 GB+ | 36 |
| Hunyuan-A13B-Instruct-8bit | 8-bit | ≈ 85.4 GB | 128 GB+ | 26 |
| Hunyuan-A13B-Instruct-bf16 | bf16 | ≈ 161 GB | 192 GB+ | 19 |