← Back to community benchmarks

Qwen2.5-7B-Instruct

M5 (10c) · 32 GB · 4bit · 2026-03-12
Performance
4k
tokens
840.7
PP tok/s
26.7
TG tok/s
4872
TTFT (ms)
4.8
Peak mem (GB)
Hardware
Chip M5 (10c)
Memory 32 GB
GPU Cores 10
Software
oMLX v0.2.9
macOS macOS 26.3
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 842.6 28.9 4.5 GB view
4k 840.7 26.7 4.8 GB current
Batching Results
Batch Size TG tok/s Speedup
28.9 1.00×
59.2 2.05×
78.2 2.71×