Changes / Feeds / Qwen/Qwen3-Coder-30B-A3B-Instruct
Qwen/Qwen3-Coder-30B-A3B-Instruct
3 changes to a tracked key since 2025-07-31, newest first. Head as last read: b2cff646eb4bb1d68355c01b18ae02e7cf42d120.
| Date | Advisory | What changed, and what it does |
|---|---|---|
| 2025-12-03 | x_NXMC-2025-0125 breaking | BOS declared as 151643 (was unset); MLP width 5472 to 6144 (2025-12-03).573fa3901e57 -> b2cff646eb4b |
| 2025-08-21 | x_NXMC-2025-0124 breaking | the chat template changed and renders differently (tool-call); prompts rendered with the old one no longer match what the model now expects, so cached prompts and eval sets need re-rendering (2025-08-21).8110d98ad896 -> 573fa3901e57 |
| 2025-08-07 | x_NXMC-2025-0123 | the chat template changed; prompts rendered with the old one no longer match what the model now expects, so cached prompts and eval sets need re-rendering (2025-08-07).703eb35446d6 -> 8110d98ad896 |
Pin it, and let a bot move the pin
from_pretrained("Qwen/Qwen3-Coder-30B-A3B-Instruct", revision="b2cff646eb4bb1d68355c01b18ae02e7cf42d120")With the Renovate preset, a pull request moves this pin when the head moves, and links back here.
[](https://www.neurarch.com/changes-feeds/models/Qwen/Qwen3-Coder-30B-A3B-Instruct.html)