What hardware does Qwen3 0.6B run on?

Tuned builds: Apple M4 Pro. plowrt also runs them on Apple M4 Max.

Does Qwen3 0.6B fit on one GPU?

Yes. The metal3-apple-m4-pro-tp1-2k build runs on one Apple M4 Pro.

Can I run Qwen3 0.6B on AMD?

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

What context length does Qwen3 0.6B support?

The upstream model supports 32,768 tokens. Our builds serve up to 2,048.

What license is Qwen3 0.6B under?

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

How do I run Qwen3 0.6B?

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

LLM 0.6B 32k native context bf16 Apache-2.0

Qwen3 0.6B

Qwen's smallest Qwen3, published for Apple Silicon.

Qwen/Qwen3-0.6B

Specs

Developer: Qwen team, Alibaba
Parameters: 0.6B
Task: LLM
Context: 32,768 tokens upstream, 2,048 served by our builds
Precisions: bf16
License: Apache-2.0
Checkpoint: Qwen/Qwen3-0.6B
Updated: 28 Oct 2026

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

Tuned for

Apple M4 Pro

Runs as-is on Apple M4 Max

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 qwen3-0.6b --fetch-weights
```
Pull with weights

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

Serve

curl -s http://127.0.0.1:8080/v1/chat/completions \
  -H 'content-type: application/json' \
  -d '{"model":"qwen3-0.6b","messages":[{"role":"user","content":"Hello"}]}'

Try it

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

Apple M4 Pro 18 GiB, also Apple M4 Max bf16 unified memory 2k Published

plowrt load infervisor/qwen3-0.6b:metal3-apple-m4-pro-tp1-2k --fetch-weights

This build only

Target: metal3-apple-m4-pro-tp1-2k , tuned on Apple M4 Pro; runs as-is on Apple M4 Max; other hardware runs it untuned
Checkpoint: Qwen/Qwen3-0.6B
Published: 28 Oct 2026
Compiled by: plowc 0.1.3 , from this recipe

About

An Apple bundle is the packet, build manifest and config: plowrt serve compiles the Metal pipelines from it on first load.

Questions

What hardware does Qwen3 0.6B run on?: Tuned builds: Apple M4 Pro. plowrt also runs them on Apple M4 Max.
Does Qwen3 0.6B fit on one GPU?: Yes. The metal3-apple-m4-pro-tp1-2k build runs on one Apple M4 Pro.
Can I run Qwen3 0.6B on AMD?: Not with a tuned build yet. Today's builds are for Apple.
What context length does Qwen3 0.6B support?: The upstream model supports 32,768 tokens. Our builds serve up to 2,048.
What license is Qwen3 0.6B under?: Apache-2.0. Check the checkpoint's license on Hugging Face before commercial use.
How do I run Qwen3 0.6B?: Install plowrt, then run plowrt load qwen3-0.6b --fetch-weights and plowrt serve --model qwen3-0.6b --port 8080. It serves an OpenAI-compatible API.