Hunyuan-A13B-Instruct-FP8
Support summary
Hunyuan-A13B-Instruct-FP8 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.
- Documented quantization
- FP8
- Configured context
- 32,768 tokens
- License
- tencent-hunyuan-a13b
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
- text generation
- License
- tencent-hunyuan-a13b
- Library
- transformers
- Architecture
- HunYuanMoEV1ForCausalLM
- Weight tensor elements
- 80.4B
- Tensor types
- BF16, F8_E4M3
- Quantization
- fp8
- Configured context
- 32,768 tokens
- Weight access
- Public
- Repository created
- 2025-06-26
Model notes and sources
- vLLM v0.28.0 · docs/models/supported_models.md · 20 indexed revisions, v0.17.0 to v0.28.0
- tencent/Hunyuan-A13B-Instruct-FP8 · publisher model card
- tencent/Hunyuan-A13B-Instruct-FP8 · Hugging Face metadata
- tencent/Hunyuan-A13B-Instruct-FP8 · publisher configuration
- vllm · models/tencent/Hunyuan-A13B-Instruct.yaml
- Reviewed
Engine support
3 engines
| Engine | Release | Checkpoint support | Evidence scope | Last known supported |
|---|---|---|---|---|
| vLLM | 0.28.0Newest indexed | Checkpoint evidenceSource: vLLM v0.28.0 · docs/models/supported_models.mdReviewed | 0.28.0This release | |
Features, dependencies and evidence for vLLM 0.28.0 | ||||
| SGLang | 0.5.19Newest indexed | No matching evidence curated | No supported release indexed | |
Features, dependencies and evidence for SGLang 0.5.19 | ||||
| TensorRT-LLM | 1.2.1Newest indexed | No matching evidence curated | No supported release indexed | |
Features, dependencies and evidence for TensorRT-LLM 1.2.1 | ||||