Changes / Feeds / Qwen/Qwen3-4B-Instruct-2507

Qwen/Qwen3-4B-Instruct-2507

1 change to a tracked key since 2025-08-05, newest first. Head as last read: cdbee75f17c01a7cc42f958dc650907174af0554.

GPU memory to fine-tune it, card by card: Qwen3-4B-Instruct-2507 on /m/.

Date	Advisory	What changed, and what it does
2025-09-17	x_NXMC-2025-0064	the chat template text changed but rendered byte-identically on the fixed conversation set (system+user, multi-turn, tool call); tokenizer model_max_length 262144 to 1010000; truncation defaults change (2025-09-17). `1b4199c4f36b -> cdbee75f17c0`

Pin it, and let a bot move the pin

from_pretrained("Qwen/Qwen3-4B-Instruct-2507", revision="cdbee75f17c01a7cc42f958dc650907174af0554")

With the Renovate preset, a pull request moves this pin when the head moves, and links back here.

config changes badge

[![config changes](https://img.shields.io/endpoint?url=https%3A%2F%2Fwww.neurarch.com%2Fchanges-feeds%2Fbadge%2FQwen%2FQwen3-4B-Instruct-2507.json)](https://www.neurarch.com/changes-feeds/models/Qwen/Qwen3-4B-Instruct-2507.html)

Renovate datasource Badge JSON On Hugging Face Memory and fit