D3 Flash leads 18 local decision configurations on an RTX 2060 6 GB

#3
by etsabary - opened

D3 Flash is the highest-scoring local configuration in my System 1 decision benchmark: 995/1,342 correct (74.1%), with a 408 ms median. The comparison now covers 49 routes, including 18 local configurations, on the same 31-category text bank.

I deliberately used an older RTX 2060 with 6 GB VRAM to explore a more accessible setup that readers may already have. The local D3 run used Artemis IQ3_M, served through Ollaya 0.17.0 over the LAN, one request at a time. Loading and warm-up calls are excluded.

Local configuration Accuracy Median p95
D3 Flash Artemis 9B 74.1% 408 ms 701 ms
Perplexity Flash v1.2 mixed4 72.4% 798 ms 1,526 ms
H2O-Lightning 4B Q8_0 66.5% 259 ms 459 ms

D3 scored 43/46 on if-then rules, 40/43 on planning, and 48/51 on explicit preference ordering. Sequential procedures scored 14/48, and spatial tracking 22/49. Three requests exceeded this local runtime's input batch limit and remain unsuccessful in the full-bank score.

The hosted d3-turbo run scored 1,106/1,342 (82.4%), with a 165 ms median and 298 ms p95—the third-lowest median among the 27 hosted decision routes. That run was measured October 20; the local runs October 25, 2026. These are different serving setups.

Full results, questions, category profiles and methods · GitHub repository

All 18 local configurations: accuracy and response time on RTX 2060 6 GB

vLLM Semantic Router org

@etsabary Great work! Thanks for Sharing

vLLM Semantic Router org

Thanks for helping test it out! @etsabary

Sign up or log in to comment