Hunyuan A13B Instruct 5bit is an open-source language model by mlx-community. Features: 80.4b LLM, VRAM: 55.8GB, Context: 32K, License: other, Quantized, Instruction-Based, LLM Explorer Score: 0.2.
| LLM Name | Hunyuan A13B Instruct 5bit |
| Repository 🤗 | https://huggingface.co/mlx-community/Hunyuan-A13B-Instruct-5bit |
| Base Model(s) | |
| Model Size | 80.4b |
| Required VRAM | 55.8 GB |
| Updated | 2026-04-05 |
| Maintainer | mlx-community |
| Model Type | hunyuan |
| Instruction-Based | Yes |
| Model Files | |
| Quantization Type | 5bit |
| Model Architecture | HunYuanMoEV1ForCausalLM |
| License | other |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.41.2 |
| Tokenizer Class | HYTokenizer |
| Padding Token | <|pad|> |
| Vocabulary Size | 128167 |
| Torch Data Type | bfloat16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Hunyuan A13B Instruct 4bit | 32K / 45.4 GB | 51 | 4 |
| Hunyuan A13B Instruct Hf | 32K / 160.8 GB | 4 | 6 |
🆘 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! 🌟