← Back to community benchmarks
Qwen2.5-3B-Instruct
Performance
8k
tokens
482.3
PP tok/s
30.5
TG tok/s
16987
TTFT (ms)
3.1
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.2.6
macOS
macOS 26.0.1
Context
8,192