← Back to community benchmarks

Qwen3.5-4B

M4 Pro (20c) · 64 GB · 4bit · 2026-04-15
Performance
8k
tokens
499.6
PP tok/s
148.1
TG tok/s
16397
TTFT (ms)
6.0
Peak mem (GB)
Hardware
Chip M4 Pro (20c)
Memory 64 GB
GPU Cores 20
Software
oMLX v0.3.5
macOS macOS 26.3
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
4k 591.7 149.9 5.7 GB view
8k 499.6 148.1 6.0 GB current