Qwen3-30B-A3B-Instruct-2507-FP8
Support summary
Qwen3-30B-A3B-Instruct-2507-FP8 is a checkpoint published by Qwen, built on the Qwen3MoeForCausalLM architecture. vLLM 0.28.0, the newest indexed vLLM release, documents support. TensorRT-LLM lists its architecture, but not this exact checkpoint.
- Documented hardware
- CPU
- 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
- text generation
- License
- apache-2.0
- Library
- transformers
- Architecture
- Qwen3MoeForCausalLM
- Weight tensor elements
- 30.5B
- Tensor types
- BF16, F8_E4M3
- Quantization
- fp8
- Configured context
- 262,144 tokens
- Base models
- Qwen/Qwen3-30B-A3B-Instruct-2507
- Weight access
- Public
- Repository created
- 2025-07-28
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/hardware_supported_models/cpu.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 | Architecture listed; exact checkpoint unknown | No supported release indexed | |
Features, dependencies and evidence for TensorRT-LLM 1.2.1 | ||||