This model requires you to accept the Apache 2.0 license terms before download.
Description
Qwen3-Coder 30B-A3B Instruct — Qwen's MoE coding model (48 layers, 128 experts top-8, 3B active) tuned for agentic coding, with native 262k-token context. Apache 2.0.
Tags
At a glance
| Kind | code language model |
|---|---|
| Precision | bfloat16 |
| Container size | 56.9 GiB |
| Weights inside | 56.9 GiB |
| Components | 2 |
| Licence | Apache 2.0 |
What is inside the container
A .nbx container packs every part of Qwen3-Coder-30B-A3B-Instruct — 2 components with weights, graphs and runtime settings — so one file is all the runtime needs.
| Component | Blocks | Layers | Weights |
|---|---|---|---|
| model | 0 | 48 | 56.3 GiB |
| lm_head | 0 | — | 594 MiB |
Default settings
The values the container ships with. They apply when you do not pass your own.
- Max length
- 262144
- Temperature
- 0.7
- Top-p
- 0.8
- Top-k
- 20
Memory needed
The weights of Qwen3-Coder-30B-A3B-Instruct take 56.9 GiB in bfloat16. That is the floor for the memory the runtime has to place, spread over the devices it finds; activations come on top and grow with the size and length you ask for. A measured peak per device class is not published for this model yet.
Verify what you downloaded
Every download carries its SHA-256, and the file endpoint sends it in the X-NBX-SHA256 header. The container is 56.9 GiB (61,079,601,878 bytes).
$ sha256sum Qwen3-Coder-30B-A3B-Instruct.nbx
1b66110dee203108fc6831c257e31d0e5e958e4a5683af578c18ac9c49cc1df5
Questions
What is Qwen3-Coder-30B-A3B-Instruct?
A code language model by Qwen, distributed as a bfloat16 .nbx container and licensed Apache 2.0.
How big is the download?
56.9 GiB, of which 56.9 GiB are weights.
How do I run it?
Install the runtime from the download page, then use the commands under “CLI Usage” below: neurobrix import Qwen/Qwen3-Coder-30B-A3B-Instruct, then neurobrix serve --model Qwen3-Coder-30B-A3B-Instruct.
CLI Usage
$ neurobrix import Qwen/Qwen3-Coder-30B-A3B-Instruct
$ neurobrix serve --model Qwen3-Coder-30B-A3B-Instruct
$ neurobrix run --prompt "your prompt here"
$ neurobrix stop