← Back to community benchmarks

Qwen2.5-3B-Instruct

M4 (10c) · 16 GB · 4bit · 2026-03-10
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