qwen3-coder-30b-a3b

Qwen3-Coder-30B-A3B-Instruct — a 30B mixture-of-experts coding model for agentic development work, with tool calling and a 256K context, served on Blackhole via vLLM.

Runs on p300x2 or p150x4 — see the serve profiles below.

Packaged and published with tt-model-manager 0.1.0 (manifest schema 5.1).

Quickstart

tt-model pull  raahemnabeel/qwen3-coder-30b-a3b --with-weights
tt-model serve raahemnabeel/qwen3-coder-30b-a3b

pull --with-weights downloads the Docker image and the Qwen/Qwen3-Coder-30B-A3B-Instruct weights (into your HF cache; they are not in the image). serve starts an OpenAI-compatible server on port 20000 (or the next free port, if that one is busy); the first start compiles kernels for your device, which takes several minutes, and the server is ready when it logs Application startup complete.

Use it

Point any OpenAI client at the address tt-model serve prints (port 20000 unless it was busy), with model id Qwen/Qwen3-Coder-30B-A3B-Instruct.

Serve profiles

One image serves every profile below; pick one with --profile.

profile	hardware	mesh	max_num_seqs	max_model_len
p300x2 (default)	p300x2	P300x2	32	256000
p150x4	p150x4	P150x4	32	256000

Provenance

The exact sources the image was built from — code/ in this repo is byte-identical to the model code inside the image:

component	built from
tt-metal	a local checkout — commit not published
vLLM	v0.24.0
vllm-tt-plugin	a local checkout — commit not published
code/ digest	a6b308b762bd37b3 (sha256, first 16 hex digits)
built	2026-09-09T12:44:17+00:00 by tt-model 0.1.0