Changes / Feeds / Qwen/Qwen3-VL-8B-Instruct-FP8
Qwen/Qwen3-VL-8B-Instruct-FP8
No tracked key changed across the 2 recorded revisions since 2025-10-11. Head as last read: 9cdc6310a8cb770ce18efaf4e9935334512aee45.
A quantization of Qwen/Qwen3-VL-8B-Instruct: 252 layers re-encoded; of the 498 tensors left unquantized, 498 byte-identical to the base. Compared tensor by tensor from sha256 fingerprints: 9cdc6310a8cb against Qwen/Qwen3-VL-8B-Instruct at 0c351dd01ed8. A hash is equal or not; it says nothing about what an edit does.
Pin it, and let a bot move the pin
from_pretrained("Qwen/Qwen3-VL-8B-Instruct-FP8", revision="9cdc6310a8cb770ce18efaf4e9935334512aee45")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-VL-8B-Instruct-FP8.html)