Skip to content
llm-speed
Leaderboard/model/stable-code-instruct-3b-4bit

stable-code-instruct-3b-4bit

2 workload results across 2 hardware configurations.

Fastest known config

192.5 decode tok/s

on M3 Ultra (60-core GPU) + 96GB unified via mlx see full run

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

WorkloadBackendQuantdecode tok/sprefill tok/sTTFTRun
chat-shortmlx@0.31.34bitno datano datano datar_imv_1hx7qx1

M3 Ultra (60-core GPU) + 96GB unifiedM3 Ultra (60-core GPU) + 96GB unified

WorkloadBackendQuantdecode tok/sprefill tok/sTTFTRun
chat-shortmlx@0.31.3192.5tok/s560.7tok/s226msr_y2_5y8oo97d

stable-code-instruct-3b-4bit on hardware