← Back to community benchmarks

Qwen2.5-7B-Instruct

M1 Pro (14c) · 16 GB · 4bit · 2026-04-28
Performance
4k
tokens
249.2
PP tok/s
32.9
TG tok/s
16435
TTFT (ms)
4.9
Peak mem (GB)
Hardware
Chip M1 Pro (14c)
Memory 16 GB
GPU Cores 14
Software
oMLX v0.3.8.dev3
macOS macOS 26.3.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 237.2 36.3 4.8 GB view
4k 249.2 32.9 4.9 GB current
8k 225.4 28.0 5.1 GB view
Batching Results
Batch Size TG tok/s Speedup
36.3 1.00×
47.3 1.30×
50.2 1.38×