Qwen2.5-Coder-7B-Instruct-Q4_K_M-GGUF — 145.6 tok/s on RTX 3090 · 24 GB ×2 | LocalMaxxing

入门指南排行榜 Decode calculator 模型 Organizations Reports Matrix runs 硬件基准评测市场租用 Pro API文档

语言

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.

提交速度测试

Observed performance

Run snapshot

All runs matching the filters below.

Fastest run

Median speed

Memory ceiling

Slowest run

Measured runs

#	模型	引擎	深度	输出 tok/s	预填	总 tok/s	TTFT ms	VRAM GB

Qwen2.5-Coder-7B-Instruct-Q4_K_M-GGUF — 145.6 tok/s on RTX 3090 · 24 GB ×2 | LocalMaxxing