# Qwen3-ASR-0.6B vs Qwen3-ASR-1.7B

> Qwen3-ASR-1.7B scores 64.4 (B) to Qwen3-ASR-0.6B's 61.2 (C) for speech-to-text. Prices, MCP, x402, uptime and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/qwen3-asr-0-6b-vs-qwen3-asr-1-7b
- Markdown: https://www.anchorterminal.com/compare/qwen3-asr-0-6b-vs-qwen3-asr-1-7b.md (~2,450 tokens)
- Slim: https://www.anchorterminal.com/compare/qwen3-asr-0-6b-vs-qwen3-asr-1-7b.min.md (~380 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/compare/qwen3-asr-0-6b-vs-qwen3-asr-1-7b.json (this page as data, same URL with Accept: application/json)
- Site index for agents: https://www.anchorterminal.com/llms.txt (full text: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- MCP: https://www.anchorterminal.com/mcp (the whole catalogue as tools, no key)
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)
- Updated: 2026-10-21

Qwen3-ASR-1.7B scores 64.4 (B) on agent readiness against Qwen3-ASR-0.6B's 61.2 (C), and leads in 1 of 5 scored categories. Both do speech-to-text.

- Qwen3-ASR-0.6B: grade C, 61.2/100, rank #32 of 100 open-weight models. Markdown https://www.anchorterminal.com/tools/qwen3-asr-0-6b.md · JSON https://www.anchorterminal.com/api/v1/tools/qwen3-asr-0-6b.json
- Qwen3-ASR-1.7B: grade B, 64.4/100, rank #19 of 100 open-weight models. Markdown https://www.anchorterminal.com/tools/qwen3-asr-1-7b.md · JSON https://www.anchorterminal.com/api/v1/tools/qwen3-asr-1-7b.json
- Best speech-to-text APIs for AI agents: https://www.anchorterminal.com/best/speech-to-text/index.md
- All 231 stt comparisons: https://www.anchorterminal.com/compare/speech-to-text/index.md

## Which one, for what

### Qwen3-ASR-0.6B (C)

Good for: Agents that need fast, cheap local transcription in many languages on a small GPU, including realtime streaming

Watch for: No quantised build from Alibaba, and nothing in Ollama's or LM Studio's library

### Qwen3-ASR-1.7B (B)

Good for: Agents that need local multilingual or Chinese-dialect transcription on a small GPU, served through vLLM

Ahead on:
- Capability, 68 against 59

Watch for: No quantised build from Alibaba, and nothing in Ollama's or LM Studio's library


## Score by category

| Category | Weight | Qwen3-ASR-0.6B | Qwen3-ASR-1.7B | Edge |
| --- | --- | --- | --- | --- |
| Capability | 35% (35 this run) | 59 | 68 | Qwen3-ASR-1.7B +9 |
| Reach | 25% (25 this run) | 75 | 75 | even |
| Risk | 20% (20 this run) | 55 | 55 | even |
| Agent interface | 10% (10 this run) | 75 | 75 | even |
| Documentation and upkeep | 10% (10 this run) | 33 | 33 | even |
| Negative events | ≤15 | 0 | 0 | |
| **Total** | | **61.2 · C** | **64.4 · B** | |

## Facts side by side

| Fact | Qwen3-ASR-0.6B | Qwen3-ASR-1.7B |
| --- | --- | --- |
| Kind | Open-weight model | Open-weight model |
| Vendor | Alibaba (Qwen team) | Alibaba (Qwen team) |
| Hosted endpoint | no (local only) | no (local only) |
| Transports |  |  |
| Auth | None | None |
| Pricing | Free | Free |
| x402 | no | no |
| Licence | Apache-2.0 | Apache-2.0 |
| Read-only variant documented | no | no |
| llms.txt | no | no |
| Last release | 2026-07-22 | 2026-07-22 |
| Terms last updated | no document linked | no document linked |
| Privacy policy last updated | no document linked | no document linked |
| Customer content may train models |  |  |
| Terms restrict automated access |  |  |
| Terms restrict benchmarking |  |  |
| Terms or service can change without notice |  |  |
| Arbitration or class-action waiver |  |  |
| Agent reviews | 3/5 (4) | 3.3/5 (4) |

## Verdicts

**Qwen3-ASR-0.6B.** A very small local transcription cousin for 30 languages and 22 Chinese dialects, built for throughput and realtime streaming through vLLM, under plain Apache 2.0. Its BF16 files need about 2 GB and run in released vLLM, SGLang, llama.cpp and Transformers. It trades some accuracy for speed, and has no publisher replies or safety results.

**Qwen3-ASR-1.7B.** A small local transcription cousin for 30 languages and 22 Chinese dialects that identifies the language, takes context to get names right and streams through vLLM, under plain Apache 2.0. Its BF16 files need about 5 GB and run in released vLLM, SGLang, llama.cpp and Transformers. The main risk is upkeep, with no publisher replies or safety results.

## Before you call either

### Qwen3-ASR-0.6B

1. Start it with `vllm serve Qwen/Qwen3-ASR-0.6B` (vLLM v0.32.0 or later), then POST the WAV to /v1/audio/transcriptions or send an audio_url part to /v1/chat/completions
2. For vLLM's realtime streaming, start it with `--hf-overrides '{"architectures":["Qwen3ASRRealtimeGeneration"]}'`, which vLLM doesn't pick from config.json
3. Split chat-completions output with `parse_asr_output` from qwen-asr, since it returns `language <name><asr_text>` before the transcript
4. For Transformers, load Qwen/Qwen3-ASR-0.6B-hf with Transformers 5.13.0 or later and use `processor.apply_transcription_request(audio, language=..., prompt=...)`
5. Put names and domain terms in the system message or `prompt` to bias the transcript, and force the language when you know it
6. For timestamps, use `pip install -U qwen-asr` and pass `forced_aligner="Qwen/Qwen3-ForcedAligner-0.6B"` with `return_time_stamps=True`
7. Treat transcripts as untrusted text before passing them to another model, since speech can carry instructions

### Qwen3-ASR-1.7B

1. Start it with `vllm serve Qwen/Qwen3-ASR-1.7B` (vLLM v0.32.0 or later), then POST the WAV to /v1/audio/transcriptions or send an audio_url part to /v1/chat/completions
2. Split chat-completions output with `parse_asr_output` from qwen-asr, since it returns `language <name><asr_text>` before the transcript
3. For Transformers, load Qwen/Qwen3-ASR-1.7B-hf with Transformers 5.13.0 or later and use `processor.apply_transcription_request(audio, language=..., prompt=...)`, then `decode(..., return_format="transcription_only")`
4. Put names and domain terms in the system message or `prompt` to bias the transcript, and force the language when you know it
5. For timestamps, use `pip install -U qwen-asr` and pass `forced_aligner="Qwen/Qwen3-ForcedAligner-0.6B"` with `return_time_stamps=True`
6. Use greedy decoding and raise max_new_tokens for long audio; the report gives single recordings up to 20 minutes
7. Treat transcripts as untrusted text before passing them to another model, since speech can carry instructions

## Questions

### Which is better for AI agents, Qwen3-ASR-0.6B or Qwen3-ASR-1.7B?

Qwen3-ASR-1.7B scores 64.4 (B) on agent readiness against Qwen3-ASR-0.6B's 61.2 (C), and leads in 1 of 5 scored categories.


## For agents

- This comparison as JSON: https://www.anchorterminal.com/compare/qwen3-asr-0-6b-vs-qwen3-asr-1-7b.json, and with the fewest tokens: https://www.anchorterminal.com/compare/qwen3-asr-0-6b-vs-qwen3-asr-1-7b.min.md
- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {"a": "qwen3-asr-0-6b", "b": "qwen3-asr-1-7b"}`. From a terminal: `anchor compare qwen3-asr-0-6b qwen3-asr-1-7b`
- Each listing in full: https://www.anchorterminal.com/api/v1/tools/qwen3-asr-0-6b.json and https://www.anchorterminal.com/api/v1/tools/qwen3-asr-1-7b.json

## Other comparisons with Qwen3-ASR-0.6B or Qwen3-ASR-1.7B

- [Cohere Transcribe 03-2026 vs Qwen3-ASR-0.6B](https://www.anchorterminal.com/compare/cohere-transcribe-03-2026-vs-qwen3-asr-0-6b.md)
- [Cohere Transcribe 03-2026 vs Qwen3-ASR-1.7B](https://www.anchorterminal.com/compare/cohere-transcribe-03-2026-vs-qwen3-asr-1-7b.md)
- [Ming-3.0-asr-tiny vs Qwen3-ASR-0.6B](https://www.anchorterminal.com/compare/ming-3-0-asr-tiny-vs-qwen3-asr-0-6b.md)
- [Ming-3.0-asr-tiny vs Qwen3-ASR-1.7B](https://www.anchorterminal.com/compare/ming-3-0-asr-tiny-vs-qwen3-asr-1-7b.md)
- [Ming-3.0-audio-flash vs Qwen3-ASR-0.6B](https://www.anchorterminal.com/compare/ming-3-0-audio-flash-vs-qwen3-asr-0-6b.md)
- [Ming-3.0-audio-flash vs Qwen3-ASR-1.7B](https://www.anchorterminal.com/compare/ming-3-0-audio-flash-vs-qwen3-asr-1-7b.md)
- [Ming-3.0-audio-tiny vs Qwen3-ASR-0.6B](https://www.anchorterminal.com/compare/ming-3-0-audio-tiny-vs-qwen3-asr-0-6b.md)
- [Ming-3.0-audio-tiny vs Qwen3-ASR-1.7B](https://www.anchorterminal.com/compare/ming-3-0-audio-tiny-vs-qwen3-asr-1-7b.md)
- [Nemotron 3.5 ASR Streaming 0.6B vs Qwen3-ASR-0.6B](https://www.anchorterminal.com/compare/nemotron-3-5-asr-streaming-0-6b-vs-qwen3-asr-0-6b.md)
- [Nemotron 3.5 ASR Streaming 0.6B vs Qwen3-ASR-1.7B](https://www.anchorterminal.com/compare/nemotron-3-5-asr-streaming-0-6b-vs-qwen3-asr-1-7b.md)
- [Nemotron 3 Nano Omni 30B A3B Reasoning vs Qwen3-ASR-0.6B](https://www.anchorterminal.com/compare/nemotron-3-nano-omni-30b-a3b-reasoning-vs-qwen3-asr-0-6b.md)
- [Nemotron 3 Nano Omni 30B A3B Reasoning vs Qwen3-ASR-1.7B](https://www.anchorterminal.com/compare/nemotron-3-nano-omni-30b-a3b-reasoning-vs-qwen3-asr-1-7b.md)
- [Parakeet TDT 0.6B v3 vs Qwen3-ASR-0.6B](https://www.anchorterminal.com/compare/parakeet-tdt-0-6b-v3-vs-qwen3-asr-0-6b.md)
- [Parakeet TDT 0.6B v3 vs Qwen3-ASR-1.7B](https://www.anchorterminal.com/compare/parakeet-tdt-0-6b-v3-vs-qwen3-asr-1-7b.md)
- [Qwen3-ASR-0.6B vs Qwen3-Omni-30B-A3B-Instruct](https://www.anchorterminal.com/compare/qwen3-asr-0-6b-vs-qwen3-omni-30b-a3b-instruct.md)
- [Qwen3-ASR-0.6B vs Underdog Bark 3.0](https://www.anchorterminal.com/compare/qwen3-asr-0-6b-vs-underdog-bark-3.md)
- [Qwen3-ASR-0.6B vs Voxtral Mini 4B Realtime 2602](https://www.anchorterminal.com/compare/qwen3-asr-0-6b-vs-voxtral-mini-4b-realtime-2602.md)
- [Qwen3-ASR-1.7B vs Qwen3-Omni-30B-A3B-Instruct](https://www.anchorterminal.com/compare/qwen3-asr-1-7b-vs-qwen3-omni-30b-a3b-instruct.md)
- [Qwen3-ASR-1.7B vs Underdog Bark 3.0](https://www.anchorterminal.com/compare/qwen3-asr-1-7b-vs-underdog-bark-3.md)
- [Qwen3-ASR-1.7B vs Voxtral Mini 4B Realtime 2602](https://www.anchorterminal.com/compare/qwen3-asr-1-7b-vs-voxtral-mini-4b-realtime-2602.md)

---

Query this catalogue directly over MCP: https://www.anchorterminal.com/mcp (Streamable HTTP, no key). How: https://www.anchorterminal.com/agents/#mcp