← Back to community benchmarks

Qwen3.5-4B

M2 Pro (19c) · 16 GB · 4bit · 2026-03-12
Performance
4k
tokens
373.5
PP tok/s
57.1
TG tok/s
10966
TTFT (ms)
4.2
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 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 371.5 61.3 4.0 GB view
4k 373.5 57.1 4.2 GB current
Batching Results
Batch Size TG tok/s Speedup
61.3 1.00×
77.9 1.27×
84.8 1.38×