Two one-Spark recipes, one Official A board test.
This is a AI post classified by Jev as AI infra & evals (a model release), kept by the AI Radar because it carries real work, not commentary.
Two one-Spark recipes, one Official A board test. MiaAI-Lab's NVFP4 vLLM kit and vcruz305's EXL3 TabbyAPI recipe both serve Qwen3.8-Flash-Next on one DGX Spark. Official A, thinking off: 137/157 and 140/157. Both teams earned that. Both enable local inference. Both are incredible recipes. Testing orchestrated while I was at 30,000 feet Full write up by Nemo at https://www.smfclearinghouse.com/blog/2026-09-20-qwen38-two-recipes-official-a/
Posted by Mike Gannotti (53.1k followers) 1 h ago · 1 likes · 185 views · view the original post on X. Kept by the AI Radar as AI infra & evals. Tools mentioned: SMF Clearinghouse.
More AI work like this
- anyone wanting to fine-tune an LLM on their own data after reading this: — @DataChaz
- Bringing AI into the enterprise doesn’t have to mean starting from scratch. — @AMD
- I've been trying to explain something to a few people this week, and I want to just put… — @volatilemarkts
- We are cooked. I made the Prediction once the M5 Ultra drops, These will be impossible… — @TechMDAI
- Wafer just dropped an AI performance engineering repo that covers: — @Hesamation
- How I AI: spend 9¢ to look at ~1750 PRs and group them into thematic investments. 17,364… — @clairevo
- Last night, in a basement in Florida, one conversation ran across two kinds of silicon… — @volatilemarkts
- I have to retract what I posted as the fastest speed of Qwen 3.8 Flash on a single DGX… — @yume_arasaki
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 35.2k posts from 5k X accounts over the last 14 days, 1.5k tools, 19 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-20 23:41 UTC. Full method.