← Back to community benchmarks

Qwen3.6-27B-oQ8-mtp

M5 Max (40c) · 128 GB · 8bit · 2026-05-17
Performance
8k
tokens
806.3
PP tok/s
28.1
TG tok/s
10160
TTFT (ms)
31.3
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.9.dev2
macOS macOS 26.4.1
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 699.5 29.9 28.8 GB view
4k 837.4 28.5 30.3 GB view
8k 806.3 28.1 31.3 GB current
16k 726.7 26.7 32.8 GB view
32k 645.4 26.1 35.8 GB view
Batching Results
Batch Size TG tok/s Speedup
29.9 1.00×
35.3 1.18×
47.9 1.60×