← Back to community benchmarks

Qwen2.5-7B-Instruct

M4 Pro (16c) · 24 GB · 4bit · 2026-03-09
Performance
1k
tokens
400.4
PP tok/s
54.2
TG tok/s
2557
TTFT (ms)
4.8
Peak mem (GB)
Hardware
Chip M4 Pro (16c)
Memory 24 GB
GPU Cores 16
Software
oMLX v0.2.6
macOS macOS 26.3.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 400.4 54.2 4.8 GB current
4k 397.1 49.6 4.9 GB view
Batching Results
Batch Size TG tok/s Speedup
54.2 1.00×
83.5 1.54×
92.7 1.71×