Changes / Feeds / Qwen/Qwen3-VL-Embedding-8B
Qwen/Qwen3-VL-Embedding-8B
No tracked key changed across the 2 recorded revisions since 2026-01-07. Head as last read: 2c4565515e0f265c6511776e7193b22c0968ddc7.
Differs from Qwen/Qwen3-VL-8B-Instruct in 216 of 749 aligned tensors (at most 77.9% of elements); 0 added and 1 dropped; the other 533 are byte-identical. Compared tensor by tensor from sha256 fingerprints: 2c4565515e0f 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-Embedding-8B", revision="2c4565515e0f265c6511776e7193b22c0968ddc7")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-Embedding-8B.html)