← Back to community benchmarks
Qwen2.5-7B-Instruct
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