Hunyuan-A13B-Pretrain

Checkpointtencent/Hunyuan-A13B-PretrainModel card indexedModel card

Support summary

Hunyuan-A13B-Pretrain is a checkpoint published by Tencent, built on the HunYuanMoEV1ForCausalLM 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.

Configured context
32,768 tokens
License
tencent-hunyuan-a13b
Hugging Face model card
Publisher
Tencent
Task
text generation
Library
transformers
Architecture
HunYuanMoEV1ForCausalLM
Weight tensor elements
80.4B
Tensor types
F32, BF16
Configured context
32,768 tokens
Weight access
Public
Repository created
2025-06-27
Source 1: tencent/Hunyuan-A13B-Pretrain · publisher model cardSource 2: tencent/Hunyuan-A13B-Pretrain · Hugging Face metadataSource 3: tencent/Hunyuan-A13B-Pretrain · publisher configurationReviewed
Model notes and sources

Engine support

3 engines

Engine support for Hunyuan-A13B-Pretrain
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