Changes / Feeds / poolside/Laguna-S-2.1-NVFP4
poolside/Laguna-S-2.1-NVFP4
3 changes to a tracked key since 2026-07-21, newest first. Head as last read: 826aacdf6d8b2699d4e367def6f17c83b06044c2.
GPU memory to fine-tune it, card by card: Laguna-S-2.1-NVFP4 on /m/.
| Date | Advisory | What changed, and what it does |
|---|---|---|
| 2026-08-01 | x_NXMC-2026-0025 breaking | context window 262144 to 1048576 tokens; quantization_config changed; the stored format of the weights is different (2026-08-01).07614121b318 -> f8fdfcdc4e7b |
| 2026-07-22 | x_NXMC-2026-0024 breaking | quantization_config changed; the stored format of the weights is different (2026-07-22).b482b5d57fda -> 07614121b318 |
| 2026-07-21 | x_NXMC-2026-0023 breaking | the chat template changed and renders differently (system+user, multi-turn, tool-call); prompts rendered with the old one no longer match what the model now expects, so cached prompts and eval sets need re-rendering; generation defaults changed (max_new_tokens 32768 to unset); a call that does not pass these explicitly now generates differently (2026-07-21).ea64155234b7 -> b482b5d57fda |
Pin it, and let a bot move the pin
from_pretrained("poolside/Laguna-S-2.1-NVFP4", revision="826aacdf6d8b2699d4e367def6f17c83b06044c2")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/poolside/Laguna-S-2.1-NVFP4.html)