DeepSeek V4.1 Flash 763B MoE on two DGX Sparks: 103 tok/s on JSON, 89 on code
A 2.9bpw exl3 build of the 763B MoE split across two DGX Sparks over QSFP hits 102.8 tok/s on JSON and 88.7 on code, reads an 8k prompt in 3.0s, and scores 76.8% on GPQA Diamond.
deepseek-v4.1-flash-1017 (763b moe) on two dgx sparks: 103 tok/s on json, 89 on code. @MiaAI_lab's 2.9 bpw exl3 build (v1) and two-spark recipe, on @ashxhart's tensorfold. one half of the model on each spark, linked over qsfp. decode, tok/s (median of 5, temperature 0.7, one user, dspark draft on): json 102.8 code 88.7 explain 72.8 story 57.3 an 8k-token prompt reads in 3.0 s. the weights load in 27 s. quality, thinking off: gpqa diamond 76.8%, ifeval 88.5%. the best ornith-1.5-122b scores i measured were 74.2 (q4_k_m) and 82.0 (nvfp4) on the same set. gpqa is within noise of ornith's. i could not run the full model, so no reference for it.
This post quotes another post: x.com/miaai_lab/status/2112105974546694249