← Back to community benchmarks

Qwen2.5-7B-Instruct

M5 (10c) · 32 GB · 4bit · 2026-03-12
Performance
1k
tokens
837.3
PP tok/s
28.9
TG tok/s
1223
TTFT (ms)
4.5
Peak mem (GB)
Hardware
Chip M5 (10c)
Memory 32 GB
GPU Cores 10
Software
oMLX v0.2.9
macOS macOS 26.3
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 837.3 28.9 4.5 GB current
4k 851.2 26.5 4.8 GB view
Batching Results
Batch Size TG tok/s Speedup
28.9 1.00×
57.7 2.00×
82.5 2.85×