What are the hardware requirements for Hunyuan A13B Instruct?

Hunyuan A13B Instruct requires approximately 161.1 GB of VRAM and supports a context window of 32K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Hunyuan A13B Instruct and how large is it?

Hunyuan A13B Instruct is developed by tencent, a model with 80.4b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Hunyuan A13B Instruct?

Hunyuan A13B Instruct is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Hunyuan A13B Instruct by tencent — VRAM 161.1GB, 32K context

Name: Hunyuan A13B Instruct
Author: tencent

Hunyuan A13B Instruct is an open-source language model by tencent. Features: 80.4b LLM, VRAM: 161.1GB, Context: 32K, License: other, Instruction-Based, LLM Explorer Score: 0.3.

Conversational Custom code Endpoints compatible Eval-results Hunyuan v1 moe Instruct Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/tencent/Hunyuan-A13B-Instruct

Hunyuan A13B Instruct Parameters and Internals

LLM Name	Hunyuan A13B Instruct
Repository 🤗	https://huggingface.co/tencent/Hunyuan-A13B-Instruct
Model Size	80.4b
Required VRAM	161.1 GB
Updated	2026-07-03
Maintainer	tencent
Model Type	hunyuan_v1_moe
Instruction-Based	Yes
Model Files	5.0 GB: 1-of-33 5.0 GB: 2-of-33 5.0 GB: 3-of-33 5.0 GB: 4-of-33 5.0 GB: 5-of-33 5.0 GB: 6-of-33 5.0 GB: 7-of-33 5.0 GB: 8-of-33 5.0 GB: 9-of-33 5.0 GB: 10-of-33 5.0 GB: 11-of-33 5.0 GB: 12-of-33 5.0 GB: 13-of-33 5.0 GB: 14-of-33 5.0 GB: 15-of-33 5.0 GB: 16-of-33 5.0 GB: 17-of-33 5.0 GB: 18-of-33 5.0 GB: 19-of-33 5.0 GB: 20-of-33 5.0 GB: 21-of-33 5.0 GB: 22-of-33 5.0 GB: 23-of-33 5.0 GB: 24-of-33 5.0 GB: 25-of-33 5.0 GB: 26-of-33 5.0 GB: 27-of-33 5.0 GB: 28-of-33 5.0 GB: 29-of-33 5.0 GB: 30-of-33 5.0 GB: 31-of-33 5.0 GB: 32-of-33 1.1 GB: 33-of-33
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

Rank the Hunyuan A13B Instruct capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Quantized Models of the Hunyuan A13B Instruct

Model	Likes	Downloads	VRAM
...unyuan A13B Instruct GPTQ Int4	53	271	42 GB
Hunyuan A13B Instruct 4bit	4	97	45 GB
Hunyuan A13B Instruct 5bit	3	73	55 GB

Best Alternatives to Hunyuan A13B Instruct

Best Alternatives	Context / RAM	Downloads	Likes
Hunyuan A13B Instruct	256K / 161.1 GB	38	2
Hunyuan A13B Instruct FP8	32K / 81 GB	573	33
Hunyuan A13B Instruct Hf	32K / 160.8 GB	9	6
Hunyuan A13B Instruct 4bit	32K / 45.4 GB	97	4
Hunyuan A13B Instruct 5bit	32K / 55.8 GB	73	3
...unyuan A13B Instruct GPTQ Int4	32K / 42.7 GB	271	53

Note: green Score (e.g. "73.2") means that the model is better than tencent/Hunyuan-A13B-Instruct.