localairecipes launch configs for local inference

Leaderboard

Refine

Source:

Model
Quant
Storage requirement
Feature tags

NVIDIA DGX Spark 128GB ×2 (Blackwell)

RecipeAA intelC1 decodeC4 decodeC8 decodePrefillTTFTEvidenceVotes
Qwen3.8-Flash-Next Uncensored NVFP4 2x DGX Spark SGLang TP2 ROCE #14040.3 tok/s117.3 tok/s120.5 tok/s2976.7 tok/s—reported0
GLM-5.3-Flash exlr8 EXL3 experts on DGX Spark TP1-4n/a128 tok/s——4393 tok/s—reported0

Machine-readable: /api/v1/leaderboard.json (these boards) · /api/v1/scores.json (per-recipe medians).