Qwen3.8-27B-NVFP4 — 2,103.6 tok/s on RTX 5090 · 32 GB | Localmaxxing

Primeiros passos Ranking Decode calculator Modelos Reports Hardware Avaliações comparativas Marketplace Aluguéis Pro Docs da API

Idioma

Observed performance

Run snapshot

Current results after the filters below are applied.

Fastest run

Median speed

Memory ceiling

Slowest run

Measured runs

Community leaderboard

Speed test results

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

Submit benchmark

Observed performance

Run snapshot

Current results after the filters below are applied.

Fastest run

Median speed

Memory ceiling

Slowest run

Measured runs

#	Hardware	Engine	Profundidade	tok/s out	Prefill	tok/s total	TTFT ms	VRAM GB

Qwen3.8-27B-NVFP4 — 2,103.6 tok/s on RTX 5090 · 32 GB | Localmaxxing