Changes / Feeds / z-lab/Qwen3.6-35B-A3B-DFlash
z-lab/Qwen3.6-35B-A3B-DFlash
2 changes to a tracked key since 2026-04-17, newest first. Head as last read: f181eece646affea2c38b2765f1aaa01a9734ccd.
GPU memory to fine-tune it, card by card: Qwen3.6-35B-A3B-DFlash on /m/.
| Date | Advisory | What changed, and what it does |
|---|---|---|
| 2026-06-19 | x_NXMC-2026-0051 breaking | EOS changed from 248046 to 248044; anything fine-tuned or served against the old value stops at a different token; layer count 8 to 6, KV heads 4 to 8; derived parameters 1.47B to 1.37B (-100.7M, -0.20 GB of bf16 weights) (2026-06-19).31977fbe13a8 -> 0ce151d016ba |
| 2026-04-17 | x_NXMC-2026-0050 breaking | rope_scaling rewritten in a different format ({"beta_fast":32,"beta_slow":1,"factor":64,"original_max_p... to {"beta_fast":32,"beta_slow":1,"factor":64,"original_max_p...); a loader that only reads the old format rejects or ignores the new one (2026-04-17).1f71bf5b8b3d -> 92297e6cfd22 |
Pin it, and let a bot move the pin
from_pretrained("z-lab/Qwen3.6-35B-A3B-DFlash", revision="f181eece646affea2c38b2765f1aaa01a9734ccd")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/z-lab/Qwen3.6-35B-A3B-DFlash.html)