← Back to community benchmarks

Qwen3.6-27B-PARO

M5 Max (40c) · 64 GB · 4bit · 2026-06-19
Performance
1k
tokens
554.8
PP tok/s
34.4
TG tok/s
1846
TTFT (ms)
15.5
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.4.4
macOS macOS 26.5.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 554.8 34.4 15.5 GB current
4k 812.2 33.7 16.7 GB view
8k 821.6 33.0 17.4 GB view
16k 697.2 31.6 18.6 GB view
32k 643.5 29.9 21.1 GB view
64k 548.8 25.6 26.2 GB view
Batching Results
Batch Size TG tok/s Speedup
34.4 1.00×
44.8 1.30×
131.6 3.83×