What are the hardware requirements for Hunyuan 4B Pretrain?

Hunyuan 4B Pretrain requires approximately 8.5 GB of VRAM and supports a context window of 256K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Hunyuan 4B Pretrain and how large is it?

Hunyuan 4B Pretrain is developed by tencent, a model with 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 4B Pretrain?

Hunyuan 4B Pretrain is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Hunyuan 4B Pretrain by tencent — VRAM 8.5GB, 256K context

Name: Hunyuan 4B Pretrain
Author: tencent

Hunyuan 4B Pretrain is an open-source language model by tencent. Features: 4b LLM, VRAM: 8.5GB, Context: 256K, LLM Explorer Score: 0.2.

Conversational Endpoints compatible Hunyuan v1 dense Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/tencent/Hunyuan-4B-Pretrain

Hunyuan 4B Pretrain Parameters and Internals

LLM Name	Hunyuan 4B Pretrain
Repository 🤗	https://huggingface.co/tencent/Hunyuan-4B-Pretrain
Model Size	4b
Required VRAM	8.5 GB
Updated	2026-08-06
Maintainer	tencent
Model Type	hunyuan_v1_dense
Model Files	5.0 GB: 1-of-2 3.5 GB: 2-of-2
Model Architecture	HunYuanDenseV1ForCausalLM
Context Length	262144
Model Max Length	262144
Transformers Version	4.52.4
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	<｜hy_▁pad▁｜>
Vocabulary Size	120818
Torch Data Type	bfloat16

Rank the Hunyuan 4B Pretrain 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 4B Pretrain

Model	Likes	Downloads	VRAM
Hunyuan 0.5B Instruct AWQ Int4	3	51	0 GB

Best Alternatives to Hunyuan 4B Pretrain

Best Alternatives	Context / RAM	Downloads	Likes
Hunyuan 4B Instruct	256K / 8.5 GB	341	30
Hunyuan 4B Instruct FP8	256K / 4.6 GB	29	3
Hunyuan 1.8B Instruct FP8	256K / 2 GB	28	2
Hunyuan 0.5B Instruct AWQ Int4	256K / 0.5 GB	51	3
Hunyuan 4B Instruct AWQ Int4	256K / 2.7 GB	41	1
Hunyuan 4B Instruct GPTQ Int4	256K / 2.8 GB	29	2

Note: green Score (e.g. "73.2") means that the model is better than tencent/Hunyuan-4B-Pretrain.