Qwen3.8-Flash-Next on any consumer hardware: one-click install for Windows / Linux. Strata inference engine, OpenAI/Anthropic API on localhost, optional image input.
C++
docs/DGX_SPARK_LINUX.md: the 61-task quality suite with the sm_121 defaults on and off
Niko12214daa83e75f2f
diff --git a/docs/DGX_SPARK_LINUX.md b/docs/DGX_SPARK_LINUX.mdindex 247af7801..0c6cbaa07 100644--- a/docs/DGX_SPARK_LINUX.md+++ b/docs/DGX_SPARK_LINUX.md@@ -130,7 +130,7 @@ which drafts to try, and the target checks every draft). 24 short greedy promptsdoes move: IQ3_S mean KL 0.019 (largest 0.082), NVFP4 0.032 (largest 0.126); the most likely token changed on 2 of 24 prompts for each, inIQ3_S's case a near tie both times (0.20 against 0.20, 0.15 against 0.14); and a 24-token greedy answer stayed the same on 1 of 6 prompts. Two runsof the same setting gave identical logits, so the difference is the switches, not noise. All of the IQ3_S difference comes from the fused-prompt path, and all of the NVFP4 difference from `w4a4`. If you want the answers of 0.2.7, set `STRATA_SM121_PERF=0`: you keep the other+prompt path, and all of the NVFP4 difference from `w4a4`. On the 61-task quality suite (long-document retrieval, extraction of up to 72 exact rows, summaries, code, JSON, agent loops with tools), run through the server with the switches on and off: IQ3_S passed 56 tasks on and 51 off, NVFP4 56 on and 52 off. Retrieval found all 63 facts in every run, and no agent loop made an invalid tool call. The extraction facts were equal on IQ3_S (621 of 642 both ways); on NVFP4 one 40-row register lost a row with the switches on (616 against 621 of 642). One summary in each model gained or lost a flagged name or figure. Answers differ in wording on 21 of 61 tasks (IQ3_S) and 25 of 61 (NVFP4), and the wins and losses go both ways, so read the suite as "no loss we could measure", not as an improvement. The same setting run twice gave identical answers, so every difference comes from the switches. If you want the answers of 0.2.7, set `STRATA_SM121_PERF=0`: you keep the otherSpark settings and lose the prompt speed-up.With `"parallel": 4` (the default) the set adds up: 32 clients at 2,000-token prompts read 41.3 tok/s with all four on and 35.7 with all off. At