← Back to community benchmarks

Qwen3.5-4B

M5 Pro (20c) · 48 GB · 4bit · 2026-07-20
Performance
64k
tokens
1,341
PP tok/s
44.2
TG tok/s
48876
TTFT (ms)
9.9
Peak mem (GB)
Hardware
Chip M5 Pro (20c)
Memory 48 GB
GPU Cores 20
Software
oMLX v0.5.1
macOS macOS 27.0
Context 65,536
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
4k 2,419 79.4 4.1 GB view
16k 2,091 31.5 5.3 GB view
64k 1,341 44.2 9.9 GB current