DeepSeek-V4.1-Flash-1017 on one RTX 3090: Big updates to the Delta Inference Engine v0.93. Same 41 tok/s at 192GB/IQ2 at better quality, usable from 64 GB RAM, first token ~40% sooner, new Unsloth quants at full speed, EXL3, basic multi-GPU, public CI and more
This item was curated into the RUSH Morning Brief from its original publisher. Open the source for the full article, then explore related AI signals on RUSH.