What are the hardware requirements for Qwen3 ASR 0.6B?

Qwen3 ASR 0.6B requires approximately 1.9 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Qwen3 ASR 0.6B and how large is it?

Qwen3 ASR 0.6B is developed by Qwen, a model with 0.6b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Qwen3 ASR 0.6B?

Qwen3 ASR 0.6B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Qwen3 ASR 0.6B by Qwen — VRAM 1.9GB

Name: Qwen3 ASR 0.6B
Author: Qwen

Qwen3 ASR 0.6B is an open-source language model by Qwen. Features: 0.6b LLM, VRAM: 1.9GB, License: apache-2.0, LLM Explorer Score: 0.37.

Arxiv:2601.21337 Automatic-speech-recognition Deploy:azure Eval-results Qwen3 asr Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/Qwen/Qwen3-ASR-0.6B

Qwen3 ASR 0.6B Parameters and Internals

LLM Name	Qwen3 ASR 0.6B
Repository 🤗	https://huggingface.co/Qwen/Qwen3-ASR-0.6B
Model Size	0.6b
Required VRAM	1.9 GB
Updated	2026-07-26
Maintainer	Qwen
Model Type	qwen3_asr
Model Files	1.9 GB
Model Architecture	Qwen3ASRForConditionalGeneration
License	apache-2.0
Model Max Length	131072
Transformers Version	4.57.6
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Errors	replace

Rank the Qwen3 ASR 0.6B capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation