localairecipes launch configs for local inference

Leaderboard

Sort by Then by

NVIDIA DGX Spark 128GB ×2 (Blackwell)

Recipe	AA intel	C1 decode	C4 decode	C8 decode	Prefill	TTFT	Evidence	Votes
GLM-5.3-Flash NVFP4 on 2x DGX Spark - Atlas RC4.2 TP2, DFlash2, 1M #1	42	91.7 tok/s	70.9 tok/s	—	—	—	reported	0
Qwen3.8-Flash-Next Uncensored NVFP4 2x DGX Spark SGLang TP2 ROCE	40	40.3 tok/s	117.3 tok/s	120.5 tok/s	2976.7 tok/s	—	reported	0
GLM-5.3-Flash exlr8 EXL3 experts on DGX Spark TP1-4	n/a	128 tok/s	—	—	4393 tok/s	—	reported	0
Motif-3 NVFP4 314B 2x DGX Spark TP2 vLLM Fork FP8 Dense MTP	n/a	19 tok/s	—	—	—	300 ms	reported	0

NVIDIA RTX PRO 6000 Blackwell 96GB ×2

Recipe	AA intel	C1 decode	C4 decode	C8 decode	Prefill	TTFT	Evidence	Votes
DeepSeek-V4.1-Flash-1017 EXL3 3bpw 2x RTX PRO 6000 Engram on SSD #1	45	167.3 tok/s	307.3 tok/s	—	7360 tok/s	—	reported	0
GLM-5.3-Flash QAD (CSF) on 2x RTX PRO 6000 Blackwell — TP2/DCP2 MTP3	42	207 tok/s	488 tok/s	672 tok/s	—	—	reported	0
DeepSeek V4 Flash Vision on 2x RTX PRO 6000 Blackwell \x{2014} TP2 DSpark K3	35	169.2 tok/s	394.7 tok/s	—	8993 tok/s	—	reported	0
DeepSeek V4 Flash-0731 on 2x RTX PRO 6000 Blackwell \x{2014} TP2 DSpark K5	34	214.9 tok/s	—	611.9 tok/s	11167 tok/s	—	reported	0

NVIDIA CMP 170HX 64GB ×3 (Ampere)

Recipe	AA intel	C1 decode	C4 decode	C8 decode	Prefill	TTFT	Evidence	Votes
Qwen3.8-Flash-Next Uncensored AWQ-g32 on 3x CMP 170HX — PP3, 1M ctx, NVMe PLE, MTP-4 (givisok) #1	40	195 tok/s	—	686 tok/s	4287 tok/s	—	reported	0
Qwen3.8-Flash-Next W4A16 3x CMP 170HX PP3 NVMe PLE fp8 KV 1M (clee)	40	74.9 tok/s	—	—	4690 tok/s	223000 ms	reported	1
DeepSeek V4 Flash-0731 abliterated on 3x CMP 170HX — vLLM patched PP3 DSpark K5	34	181 tok/s	—	—	2350 tok/s	—	reported	0

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