← Back to community benchmarks

Qwen3.5-4B

M5 Pro (20c) · 48 GB · 4bit · 2026-07-20
Performance
16k
tokens
2,091
PP tok/s
31.5
TG tok/s
7837
TTFT (ms)
5.3
Peak mem (GB)
Hardware
Chip M5 Pro (20c)
Memory 48 GB
GPU Cores 20
Software
oMLX v0.5.1
macOS macOS 27.0
Context 16,384
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 current
64k 1,341 44.2 9.9 GB view