localairecipes launch configs for local inference

Leaderboard

Refine

Source:

Model
Quant
Storage requirement
Feature tags

NVIDIA RTX 5090 32GB ×1 (Blackwell)

RecipeAA intelC1 decodeC4 decodeC8 decodePrefillTTFTEvidenceVotes
DeepSeek-V4.1-Flash-1017 streaming NVMe stack on 1x RTX 5090 (fronteagle739) #14522.7 tok/s——4632 tok/s47200 msreported0

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