← Back to community benchmarks

Qwen3.5-4B

M4 Pro (20c) · 64 GB · 4bit · 2026-04-15
Performance
4k
tokens
591.7
PP tok/s
149.9
TG tok/s
6923
TTFT (ms)
5.7
Peak mem (GB)
Hardware
Chip M4 Pro (20c)
Memory 64 GB
GPU Cores 20
Software
oMLX v0.3.5
macOS macOS 26.3
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
4k 591.7 149.9 5.7 GB current
8k 499.6 148.1 6.0 GB view