LLM EXPLORER 56,604 MODELS INDEXED

Hunyuan A13B Instruct GPTQ Int4 by tencent

By tencent · 271 downloads
HF Repo ↗ Copy URL

Hunyuan A13B Instruct GPTQ Int4 is an open-source language model by tencent. Features: 80.4b LLM, VRAM: 42.7GB, Context: 32K, License: other, Quantized, Instruction-Based, LLM Explorer Score: 0.2.

  4-bit Base model:quantized:tencent/h... Base model:tencent/hunyuan-a13...   Conversational   Custom code   Endpoints compatible   Gptq   Hunyuan   Instruct   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/tencent/Hunyuan-A13B-Instruct-GPTQ-Int4 

Hunyuan A13B Instruct GPTQ Int4 Parameters and Internals

LLM NameHunyuan A13B Instruct GPTQ Int4
Repository 🤗https://huggingface.co/tencent/Hunyuan-A13B-Instruct-GPTQ-Int4 
Base Model(s)  Hunyuan A13B Instruct   tencent/Hunyuan-A13B-Instruct
Model Size80.4b
Required VRAM42.7 GB
Updated2026-08-08
Maintainertencent
Model Typehunyuan
Instruction-BasedYes
Model Files  5.0 GB: 1-of-9   5.0 GB: 2-of-9   5.0 GB: 3-of-9   5.0 GB: 4-of-9   5.0 GB: 5-of-9   5.0 GB: 6-of-9   5.0 GB: 7-of-9   5.0 GB: 8-of-9   2.7 GB: 9-of-9
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureHunYuanMoEV1ForCausalLM
Licenseother
Context Length32768
Model Max Length32768
Transformers Version4.41.2
Tokenizer ClassHYTokenizer
Padding Token<|pad|>
Vocabulary Size128167
Torch Data Typebfloat16

Best Alternatives to Hunyuan A13B Instruct GPTQ Int4

Best Alternatives
Context / RAM
Downloads
Likes
Hunyuan A13B Instruct 4bit32K / 45.4 GB974
Hunyuan A13B Instruct 5bit32K / 55.8 GB733
Hunyuan A13B Instruct256K / 161.1 GB382
Hunyuan A13B Instruct32K / 161.1 GB50352795
Hunyuan A13B Instruct FP832K / 81 GB57333
Hunyuan A13B Instruct Hf32K / 160.8 GB96
Note: green Score (e.g. "73.2") means that the model is better than tencent/Hunyuan-A13B-Instruct-GPTQ-Int4.