Changes / Feeds / Qwen/Qwen3-30B-A3B-Instruct-2507
Qwen/Qwen3-30B-A3B-Instruct-2507
6 changes to a tracked key since 2025-07-28, newest first. Head as last read: 0d7cf23991f47feeb3a57ecb4c9cee8ea4a17bfe.
| Date | Advisory | What changed, and what it does |
|---|---|---|
| 2025-09-17 | x_NXMC-2025-0099 | the chat template text changed but rendered byte-identically on the fixed conversation set (system+user, multi-turn, tool call) (2025-09-17).3ffd1f50b179 -> 0d7cf23991f4 |
| 2025-08-08 | x_NXMC-2025-0098 | tokenizer model_max_length 262144 to 1010000; truncation defaults change (2025-08-08).97f3f7d6f068 -> 3ffd1f50b179 |
| 2025-07-29 | x_NXMC-2025-0097 | generation defaults changed (temperature 0.6 to 0.7, top_p 0.95 to 0.8); a call that does not pass these explicitly now generates differently (2025-07-29).fd5492ea2461 -> 97f3f7d6f068 |
| 2025-07-29 | x_NXMC-2025-0096 | the chat template text changed but rendered byte-identically on the fixed conversation set (system+user, multi-turn, tool call); tokenizer model_max_length 131072 to 262144; truncation defaults change (2025-07-29).023ad300e0cf -> fd5492ea2461 |
| 2025-07-29 | x_NXMC-2025-0095 | generation defaults changed (temperature 0.7 to 0.6, top_p 0.8 to 0.95); a call that does not pass these explicitly now generates differently (2025-07-29).b92fe559a979 -> 023ad300e0cf |
| 2025-07-28 | x_NXMC-2025-0094 breaking | MLP width 5504 to 6144; context window 1048576 to 262144 tokens; architectures ["Qwen2MoeForCausalLM"] to ["Qwen3MoeForCausalLM"]; a different class is instantiated from the same id (2025-07-28).4457916f69bf -> e67ac5d4218a |
Pin it, and let a bot move the pin
from_pretrained("Qwen/Qwen3-30B-A3B-Instruct-2507", revision="0d7cf23991f47feeb3a57ecb4c9cee8ea4a17bfe")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/Qwen3-30B-A3B-Instruct-2507.html)