← Back to community benchmarks
Qwen2.5-3B-Instruct
Performance
1k
tokens
536.8
PP tok/s
52.2
TG tok/s
1908
TTFT (ms)
2.2
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.2.6
macOS
macOS 15.7.3
Context
1,024