Skip to content
llm-speed
Leaderboard/model/mlx-community-qwen2-5-0-5b-instruct-4bit

Qwen2.5-0.5B-Instruct-4bit

2 workload results across 1 hardware configuration.

Fastest known config

286.5 decode tok/s

on M3 Pro (18-core GPU) + 36GB unified via mlx (4bit) see full run

M3 Pro (18-core GPU) + 36GB unifiedM3 Pro (18-core GPU) + 36GB unified

WorkloadBackendQuantdecode tok/sprefill tok/sTTFTRun
chat-shortmlx@0.31.34bit286.5tok/s656.2tok/s200msr_akcbpx5vcqa
chat-shortmlx@0.31.34bit282.6tok/s668.8tok/s196msr_bftqtkilvoe

Qwen2.5-0.5B-Instruct-4bit on hardware