---
tags:
- blackhole
- p150x4
- p300x2
- tt-model-cache
- tt-model-catalog
- tt-model-container
- vllm-plugin
---

# 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](https://github.com/tenstorrent/tt-model-manager) 0.1.0 (manifest schema 5.1).

## Quickstart

```bash
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`](https://huggingface.co/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`](https://github.com/vllm-project/vllm/releases/tag/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 |