← Back to community benchmarks

Qwen2.5-7B-Instruct

M3 Ultra (60c) · 96 GB · 4bit · 2026-05-03
Performance
8k
tokens
1,225
PP tok/s
101.0
TG tok/s
6689
TTFT (ms)
5.3
Peak mem (GB)
Hardware
Chip M3 Ultra (60c)
Memory 96 GB
GPU Cores 60
Software
oMLX v0.3.8
macOS macOS 26.4.1
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
4k 1,243 114.2 4.9 GB view
8k 1,225 101.0 5.3 GB current