The Minimax paper was published in June 2026 coinciding with the Minimax M3 release - I’m not sure how the repo you posted here could have been an implementation of Minimax sparse attention when it was updated over a year ago?
I’ve actually been really interested in Minimax M3 - seems like it flew under the radar but size wise might actually be runnable for local inference with a similar footprint to Deepseek V4 flash.
Has anyone used the new Minimax M3 model? I’m curious how it compares with Deepseek V4 and GLM 5.2 and other larger open weights models.
It is pretty nice and a serious step up from M2.7. I prefer it to GLM 5.2 for simpler tasks because of the cheaper token plan.
Right now M3 is not far behind DS4, but I belive DS4 will improve much more with each round of training. It simply has a bigger brain, it just needs to fill it with more information.
5 comments
[ 2.9 ms ] story [ 21.5 ms ] threadSuch lazy, much farming
https://github.com/fla-org/native-sparse-attention?utm_sourc...
Has anyone used the new Minimax M3 model? I’m curious how it compares with Deepseek V4 and GLM 5.2 and other larger open weights models.
Right now M3 is not far behind DS4, but I belive DS4 will improve much more with each round of training. It simply has a bigger brain, it just needs to fill it with more information.