← Back to community benchmarks

Qwen3.5-4B

M2 Pro (16c) · 16 GB · 4bit · 2026-03-10
Performance
4k
tokens
320.5
PP tok/s
55.8
TG tok/s
12782
TTFT (ms)
4.2
Peak mem (GB)
Hardware
Chip M2 Pro (16c)
Memory 16 GB
GPU Cores 16
Software
oMLX v0.2.6
macOS macOS 26.3
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 321.0 59.6 4.0 GB view
4k 320.5 55.8 4.2 GB current
Batching Results
Batch Size TG tok/s Speedup
59.6 1.00×
70.1 1.18×
57.7 0.97×