← Back to community benchmarks

Qwen2.5-7B-Instruct

M5 (10c) · 32 GB · 4bit · 2026-03-11
Performance
4k
tokens
64.6
PP tok/s
6.3
TG tok/s
63414
TTFT (ms)
4.8
Peak mem (GB)
Hardware
Chip M5 (10c)
Memory 32 GB
GPU Cores 10
Software
oMLX v0.2.7
macOS macOS 26.4
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
4k 64.6 6.3 4.8 GB current
8k 89.3 2.7 5.0 GB view
16k 174.6 21.5 5.5 GB view
32k 168.9 2.3 6.5 GB view