Qwen2.5-VL-7B-Instruct-GGUF — 222.4 tok/s on RTX 5090 · 32 GB | Localmaxxing

Get started Leaderboard Decode calculator Models Reports Hardware Benchmarks Marketplace Rentals Pro API Docs

Language

Total runs

Highest

Best memory ceiling

Median

Lowest

Total runs

Highest

Best memory ceiling

Median

Lowest

Speed Test Results

Submit benchmark

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

Qwen2.5-VL-7B-Instruct-GGUF — 222.4 tok/s on RTX 5090 · 32 GB | Localmaxxing