Changes / Feeds / Qwen/Qwen3-Coder-30B-A3B-Instruct-FP8
Qwen/Qwen3-Coder-30B-A3B-Instruct-FP8
4 changes to a tracked key since 2025-07-31, newest first. Head as last read: dcaee4d4dfc5ee71ad501f01f530e5652438fde0.
| Date | Advisory | What changed, and what it does |
|---|---|---|
| 2025-12-03 | x_NXMC-2025-0093 breaking | BOS declared as 151643 (was unset); MLP width 5472 to 6144; quantization_config changed; the stored format of the weights is different (2025-12-03).e8ab3f2db9e3 -> dcaee4d4dfc5 |
| 2025-08-21 | x_NXMC-2025-0092 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).acc0a21828d8 -> e8ab3f2db9e3 |
| 2025-08-07 | x_NXMC-2025-0091 | 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).d8df4ca2367d -> acc0a21828d8 |
| 2025-07-31 | x_NXMC-2025-0090 breaking | EOS changed from 151645 to [151645,151643]; anything fine-tuned or served against the old value stops at a different token; pad token unset to 151643; batched training masks a different id; generation defaults changed (do_sample unset to true, repetition_penalty unset to 1.05, temperature unset to 0.7, top_k unset to 20); a call that does not pass these explicitly now generates differently (2025-07-31).3e3d2d849dab -> d8df4ca2367d |
Pin it, and let a bot move the pin
from_pretrained("Qwen/Qwen3-Coder-30B-A3B-Instruct-FP8", revision="dcaee4d4dfc5ee71ad501f01f530e5652438fde0")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-FP8.html)