Skip to content
llm-speed
Leaderboard/model/deepseek-coder-v2-lite-instruct-4bit

Coder-V2-Lite-Instruct-4bit

2 workload results across 2 hardware configurations.

Fastest known config

168.3 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_e5p2vp47k3b

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

WorkloadBackendQuantdecode tok/sprefill tok/sTTFTRun
chat-shortmlx@0.31.3168.3tok/s291.5tok/s449msr_l_v1-zq_qaz

Coder-V2-Lite-Instruct-4bit on hardware