Will this model run on your hardware?
Can I run Tencent: Hunyuan A13B Instruct locally?
- 80B parameters (13B active, MoE)
- context up to 32K
- licence: other
- Weights: tencent/Hunyuan-A13B-Instruct · GGUF: unsloth/Hunyuan-A13B-Instruct-GGUF
Open this page in a browser to check it against your own GPU or Mac: the tool detects your hardware locally and shows the best quantization that fits, the memory it needs and an estimated speed.
Quantizations and file sizes
| Quantization | GGUF file |
|---|---|
| Q8_0 | 85.4 GB |
| Q5_K_M | 57.1 GB |
| Q4_K_M | 48.8 GB |
| Q3_K_M | 38.6 GB |
| Q2_K | 29.4 GB |
Run it locally
ollama run hf.co/unsloth/Hunyuan-A13B-Instruct-GGUF:Q4_K_M
llama serve -hf unsloth/Hunyuan-A13B-Instruct-GGUF:Q4_K_M
LM Studio: open unsloth/Hunyuan-A13B-Instruct-GGUF