NVIDIA-Nemotron-3.5-Lightning-30B-A3B-W4A16 — 1,526.8 tok/s on Intel Arc Pro B65 · 32 GB ×2 | LocalMaxxing

시작하기 리더보드 Decode calculator 모델 Organizations Reports 하드웨어 벤치마크 마켓플레이스 렌탈 Pro API 문서

언어

Observed performance

Run snapshot

All runs matching the filters below.

Fastest run

Median speed

Memory ceiling

Slowest run

Measured runs

Community leaderboard

Speed test results

Compare real runs across hardware, engines, contexts, and quantizations.

속도 테스트 제출

Observed performance

Run snapshot

All runs matching the filters below.

Fastest run

Median speed

Memory ceiling

Slowest run

Measured runs

#	모델	엔진	깊이	출력 tok/s	프리필	총 tok/s	TTFT ms	VRAM GB

NVIDIA-Nemotron-3.5-Lightning-30B-A3B-W4A16 — 1,526.8 tok/s on Intel Arc Pro B65 · 32 GB ×2 | LocalMaxxing