← Back to community benchmarks

Qwen3.5-4B

M2 Pro (19c) · 16 GB · 4bit · 2026-03-12
Performance
1k
tokens
371.5
PP tok/s
61.3
TG tok/s
2756
TTFT (ms)
4.0
Peak mem (GB)
Hardware
Chip M2 Pro (19c)
Memory 16 GB
GPU Cores 19
Software
oMLX v0.2.9
macOS macOS 15.7.4
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 371.5 61.3 4.0 GB current
4k 373.5 57.1 4.2 GB view
Batching Results
Batch Size TG tok/s Speedup
61.3 1.00×
77.9 1.27×
84.8 1.38×