← Back to community benchmarks

Qwen3.5-27B

M5 Pro (20c) · 64 GB · 4bit · 2026-03-16
Performance
4k
tokens
478.9
PP tok/s
17.8
TG tok/s
8553
TTFT (ms)
17.0
Peak mem (GB)
Hardware
Chip M5 Pro (20c)
Memory 64 GB
GPU Cores 20
Software
oMLX v0.2.12
macOS macOS 26.3.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
4k 478.9 17.8 17.0 GB current
8k 468.6 17.3 17.4 GB view
16k 444.3 14.6 18.3 GB view
32k 413.0 11.1 20.1 GB view
64k 344.6 8.0 23.6 GB view
128k 254.2 5.2 31.0 GB view
195k 197.6 3.8 38.6 GB view