Skip to content
llm-speed
Leaderboard/model/granite-8b-code-instruct-4bit

granite-8b-code-instruct-4bit

2 workload results across 2 hardware configurations.

Fastest known config

112.3 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@0.31.3no datano datano datar_z8xsw9qmmx-

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

WorkloadBackendQuantdecode tok/sprefill tok/sTTFTRun
chat-shortmlx@0.31.3112.3tok/s525.7tok/s221msr_bue3bee0gw7

granite-8b-code-instruct-4bit on hardware