HunyuanOCR

Checkpointtencent/HunyuanOCRModel card indexedModel card

Support summary

HunyuanOCR is a checkpoint published by Tencent, built on the HunYuanVLForConditionalGeneration architecture. vLLM 0.28.0, the newest indexed vLLM release, documents support.

vLLM documents support in 20 of 20 indexed releases, from 0.17.0 to 0.28.0.

Documented quantization
BF16
Configured context
131,072 tokens
License
tencent-hunyuan-community

Hardware, quantization and features count only statements about this checkpoint; engine-wide capabilities are listed with each release.

Hugging Face model card
Publisher
Tencent
Task
image text to text
Library
transformers
Architecture
HunYuanVLForConditionalGeneration
Weight tensor elements
1.1B
Tensor types
BF16
Configured context
131,072 tokens
Languages
multilingual, en, zh
Weight access
Public
Repository created
2025-11-18
Source 1: tencent/HunyuanOCR · publisher model cardSource 2: tencent/HunyuanOCR · Hugging Face metadataSource 3: tencent/HunyuanOCR · publisher configurationReviewed
Model notes and sources

Engine support

3 engines

Engine support for HunyuanOCR
EngineReleaseCheckpoint supportEvidence scopeLast known supported
vLLM0.28.0Newest indexedCheckpoint evidenceSource: vLLM v0.28.0 · docs/models/supported_models.mdReviewed 0.28.0This release
Features, dependencies and evidence for vLLM 0.28.0
SGLang0.5.19Newest indexedNo matching evidence curatedNo supported release indexed
Features, dependencies and evidence for SGLang 0.5.19
TensorRT-LLM1.2.1Newest indexedNo matching evidence curatedNo supported release indexed
Features, dependencies and evidence for TensorRT-LLM 1.2.1

Recipes and cookbooks