Re:Flash-MSA: Accelerating Million-Token Training with Spars...
by throwa356262 on Monday July 13, 2026 @04:33AM
(#48889577)
I have used it a little bit (0.5B tokens) for agentic tasks and coding. 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.
[Update: their cheapest token plan has been removed, I guess its back to GLM now]
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.
[Update: their cheapest token plan has been removed, I guess its back to GLM now]
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.