MiniMax-M3 now is rank #8 on @ArtificialAnlys.
Due to the workload involved in open-sourcing the MSA operator in parallel, the weights will be released to everyone late next week.
@Teknium@openclaw@Teknium so looking back it was an update through the desktop and something was not 100% yet. Anyways posting this in case this helps you or others:
@Teknium@Teknium took the same option I did on @openclaw one time... fired up Codex and let it do its magic. Took a while to diagnose because of approvals... but it sure did get it fixed!!!
Gemma 4 12B can now run locally on just 8GB RAM via Dynamic GGUFs.
Google's new model, Gemma 4 12B Unified supports image, audio and 256K context.
You can run and train the model via Unsloth Studio.
GGUF: https://t.co/8cL321pVDh
Guide: https://t.co/odRo9WjRpA
@Teknium TUI working fine, Gateway is goodf... closed and reopen the UI several times and same issue... happy to try anything to get it back in order. Thanks!!!