localairecipes launch configs for local inference

Leaderboard

Refine

Source:

Model
Quant
Storage requirement
Feature tags

NVIDIA dgx-station-gb300 288GB ×2 (Blackwell)

RecipeAA intelC1 decodeC4 decodeC8 decodePrefillTTFTEvidenceVotes
DeepSeek V4.1 Flash 1017 FP8 TP1xPP2 DSpark 2x DGX Station GB300 RoCE vLLM 0.31 overlay #145391 tok/s595 tok/s974 tok/s——reported0

NVIDIA RTX PRO 6000 Blackwell 96GB ×3

RecipeAA intelC1 decodeC4 decodeC8 decodePrefillTTFTEvidenceVotes
DeepSeek-V4.1-Flash-1017 Kraken TP3 3x RTX PRO 6000 Blackwell #145271.8 tok/s474.3 tok/s—13486 tok/s—reported0

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