| LLM Name | Hunyuan A13B Instruct |
| Repository ๐ค | https://huggingface.co/tencent/Hunyuan-A13B-Instruct |
| Model Size | 80.4b |
| Required VRAM | 161.1 GB |
| Updated | 2025-09-23 |
| Maintainer | tencent |
| Model Type | hunyuan_v1_moe |
| Instruction-Based | Yes |
| Model Files | |
| Model Architecture | HunYuanMoEV1ForCausalLM |
| License | other |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.41.2 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <|pad|> |
| Vocabulary Size | 128167 |
| Torch Data Type | bfloat16 |
Model |
Likes |
Downloads |
VRAM |
|---|---|---|---|
| Hunyuan A13B Instruct 4bit | 4 | 78 | 45 GB |
| Hunyuan A13B Instruct 5bit | 2 | 25 | 55 GB |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Hunyuan A13B Instruct | 256K / 161.1 GB | 11 | 2 |
| Hunyuan A13B Instruct Hf | 32K / 160.8 GB | 1 | 6 |
| Hunyuan A13B Instruct 4bit | 32K / 45.4 GB | 78 | 4 |
| Hunyuan A13B Instruct 5bit | 32K / 55.8 GB | 25 | 2 |
๐ Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! ๐