Qwen3-VL-30B-A3B-Instruct
Support summary
Qwen3-VL-30B-A3B-Instruct is a checkpoint published by Qwen, built on the Qwen3VLMoeForConditionalGeneration 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 hardware
- CPU
- Documented quantization
- BF16
- Configured context
- 262,144 tokens
- License
- apache-2.0
Hardware, quantization and features count only statements about this checkpoint; engine-wide capabilities are listed with each release.
Hugging Face model card
- Publisher
- Qwen
- Task
- image text to text
- License
- apache-2.0
- Library
- transformers
- Architecture
- Qwen3VLMoeForConditionalGeneration
- Weight tensor elements
- 31.1B
- Tensor types
- BF16
- Configured context
- 262,144 tokens
- Weight access
- Public
- Repository created
- 2025-09-30
Model notes and sources
- vLLM v0.28.0 · docs/models/supported_models.md · 20 indexed revisions, v0.17.0 to v0.28.0
- vLLM v0.28.0 · docs/models/hardware_supported_models/cpu.md
- Qwen/Qwen3-VL-30B-A3B-Instruct · publisher model card
- Qwen/Qwen3-VL-30B-A3B-Instruct · Hugging Face metadata
- Qwen/Qwen3-VL-30B-A3B-Instruct · publisher configuration
- vllm · models/Qwen/Qwen3-VL-30B-A3B-Instruct.yaml
- Reviewed
Engine support
3 engines
| Engine | Release | Checkpoint support | Evidence scope | Last known supported |
|---|---|---|---|---|
| vLLM | Version not pinnedRecipe / cookbook | Documented recipeSource: vllm · models/Qwen/Qwen3-VL-30B-A3B-Instruct.yamlReviewed | View 0.28.0 | |
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 | ||||