Mimo 2.6 309B (15B active) Flash
on 4× Unknown GPU · 262,144 ctx
Summary
User reports MiMo-V2.6-Flash running a 262144-token prompt end to end on four ranks, with a decode step at 8 tokens of context going from 3.63 to 5.63 tokens a second.
Setup is a four-rank run of the model's own code, with a 256k prompt reaching 48.32 tok/s and a 64k prompt at chunk 4096 reaching 104.4 tok/s (95.5 at chunk 2048).
The gains come from a fixed 2^26-score row step in the attention block loop and from cutting 145 cudaStreamSynchronize calls a decode step; a free-memory budget instead of the constant measured 8246.7 s at 256k against 5424.9 s for the constant.
Compare this run
Medians of plain runs: one device, one request, no speculative decoding, the whole model in the device's memory. The report above is one setup, so read it beside them and not as one of them.