Qwen3 ASR 1.7B is an open-source language model by Qwen. Features: 1.7b LLM, VRAM: 4.7GB, License: apache-2.0, LLM Explorer Score: 0.48.
Arxiv:2601.21337 Automatic-speech-recognition Deploy:azure Eval-results Qwen3 asr Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/Qwen/Qwen3-ASR-1.7B
Qwen3 ASR 1.7B Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
Qwen3 ASR 1.7B Parameters and Internals
| LLM Name | Qwen3 ASR 1.7B |
| Repository 🤗 | https://huggingface.co/Qwen/Qwen3-ASR-1.7B |
| Model Size | 1.7b |
| Required VRAM | 4.7 GB |
| Updated | 2026-05-08 |
| Maintainer | Qwen |
| Model Type | qwen3_asr |
| Model Files | |
| 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 1.7B Capabilities
🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟
What open-source LLMs or SLMs are you in search of? 53570 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a