← Back to community benchmarks

Qwen2.5-72B-Instruct

M4 Max (40c) · 64 GB · 4bit · 2026-03-13
Performance
8k
tokens
92.0
PP tok/s
9.8
TG tok/s
89076
TTFT (ms)
41.4
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.2.10
macOS macOS 26.3.1
Context 8,192