Qwen3-ASR-1.7B

CheckpointQwen/Qwen3-ASR-1.7BModel card indexedModel card

Support summary

Qwen3-ASR-1.7B is a checkpoint published by Qwen, built on the Qwen3ASRForConditionalGeneration architecture. The newest indexed releases vLLM 0.28.0 and SGLang 0.5.19 both document support.

vLLM documents support in 20 of 20 indexed releases, from 0.17.0 to 0.28.0. SGLang documents support in 11 of 13 indexed releases, from 0.5.11 to 0.5.19.

Documented quantization
BF16
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
automatic speech recognition
License
apache-2.0
Architecture
Qwen3ASRForConditionalGeneration
Weight tensor elements
2.3B
Tensor types
BF16
Weight access
Public
Repository created
2026-01-28
Source 1: Qwen/Qwen3-ASR-1.7B · publisher model cardSource 2: Qwen/Qwen3-ASR-1.7B · Hugging Face metadataSource 3: Qwen/Qwen3-ASR-1.7B · publisher configurationReviewed
Model notes and sources

Engine support

3 engines

Engine support for Qwen3-ASR-1.7B
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 indexedCheckpoint evidenceSource: SGLang v0.5.19 · docs/docs/supported-models/multimodal_language_models.mdxReviewed 0.5.19This release
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