Hunyuan-A13B-Instruct
by tencent
80.4B params · text-generation · 616 likes · 16.5k downloads
Hunyuan-A13B-Instruct is a 80.4B parameter model. At Q4 quantization it requires 40GB of VRAM. It runs comfortably on H100 SXM5 80 GB (60 tok/s), H200 SXM 141 GB (87 tok/s).
GPU compatibility
| GPU | VRAM | Q4 Decode | Verdict |
|---|---|---|---|
| M4 Max 128GB | 128GB | 5 tok/s | tight |
| M4 Pro 48GB | 48GB | 2 tok/s | tight |
| A100 PCIe 80 GB | 80GB | 29 tok/s | tight |
| H100 SXM5 80 GB | 80GB | 60 tok/s | comfortable |
| M4 Max 64GB | 64GB | 5 tok/s | tight |
| H200 SXM 141 GB | 141GB | 87 tok/s | comfortable |
| M2 Ultra 192GB | 192GB | 8 tok/s | tight |