What hardware does Qwen3 ASR 0.6B run on?

Tuned builds: NVIDIA H100 SXM5. plowrt also runs them on H100 NVL, H200 SXM.

Does Qwen3 ASR 0.6B fit on one GPU?

Yes. The sm90a-h100-tp1 build runs on one NVIDIA H100 SXM5.

Can I run Qwen3 ASR 0.6B on AMD?

Not with a tuned build yet. Today's builds are for NVIDIA.

What context length does Qwen3 ASR 0.6B support?

The upstream model supports 65,536 tokens. Our builds serve up to 2,048.

What license is Qwen3 ASR 0.6B under?

Apache-2.0. Check the checkpoint's license on Hugging Face before commercial use.

How do I run Qwen3 ASR 0.6B?

Install plowrt, then run plowrt load qwen3-asr-0.6b --fetch-weights and plowrt serve --model qwen3-asr-0.6b --port 8080. It serves an OpenAI-compatible API.

Speech to text 0.6B 64k native context bf16 Apache-2.0

Qwen3 ASR 0.6B

The 0.6B Qwen3 ASR model, for latency-first transcription on a small GPU.

Qwen/Qwen3-ASR-0.6B

Specs

Developer: Qwen team, Alibaba
Parameters: 0.6B
Task: Speech to text
Context: 65,536 tokens upstream, 2,048 served by our builds
Precisions: bf16
License: Apache-2.0
Checkpoint: Qwen/Qwen3-ASR-0.6B
Updated: 28 Oct 2026

Where it runs Each build is tuned for one part. plowrt runs it beyond that.

Tuned for

NVIDIA H100 SXM5

Runs as-is on H100 NVL, H200 SXM

Elsewhere plowrt still runs the model on other NVIDIA, AMD and Apple hardware, without this build’s tuning: expect lower throughput.

Run it An OpenAI-compatible server on your own machine.

plowrt 0.1.3 Install, pull, serve, call

curl -fsSL https://pdist.infervisor.ai/install.sh | sh

Install

plowrt load qwen3-asr-0.6b --fetch-weights

Pull with weights

plowrt serve --model qwen3-asr-0.6b --port 8080

Serve

curl -s http://127.0.0.1:8080/v1/audio/transcriptions \
  -F model=qwen3-asr-0.6b -F file=@sample.wav

Try it

Builds `plowrt load` picks the closest fit for your machine.

NVIDIA H100 SXM5 80 GiB, also H100 NVL, H200 SXM bf16 1 GPU 2k Published

plowrt load infervisor/qwen3-asr-0.6b:sm90a-h100-tp1 --fetch-weights

This build only

Target: sm90a-h100-tp1 , tuned on NVIDIA H100 SXM5; runs as-is on H100 NVL, H200 SXM; other hardware runs it untuned
Checkpoint: Qwen/Qwen3-ASR-0.6B
Published: 28 Oct 2026
Compiled by: plowc 0.1.3 , from this recipe

About

Shares the 1.7B recipe with a smaller decoder. Pick it where a single L4 or L40S serves several speech models at once.

Questions

What hardware does Qwen3 ASR 0.6B run on?: Tuned builds: NVIDIA H100 SXM5. plowrt also runs them on H100 NVL, H200 SXM.
Does Qwen3 ASR 0.6B fit on one GPU?: Yes. The sm90a-h100-tp1 build runs on one NVIDIA H100 SXM5.
Can I run Qwen3 ASR 0.6B on AMD?: Not with a tuned build yet. Today's builds are for NVIDIA.
What context length does Qwen3 ASR 0.6B support?: The upstream model supports 65,536 tokens. Our builds serve up to 2,048.
What license is Qwen3 ASR 0.6B under?: Apache-2.0. Check the checkpoint's license on Hugging Face before commercial use.
How do I run Qwen3 ASR 0.6B?: Install plowrt, then run plowrt load qwen3-asr-0.6b --fetch-weights and plowrt serve --model qwen3-asr-0.6b --port 8080. It serves an OpenAI-compatible API.