← Back to community benchmarks

Qwen3.6-27B-oQ6-mtp

M5 Max (40c) · 128 GB · 6bit · 2026-05-22
Performance
64k
tokens
530.7
PP tok/s
17.9
TG tok/s
123489
TTFT (ms)
35.6
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.9
macOS macOS 26.4.1
Context 65,536
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 743.5 23.8 22.6 GB view
4k 825.1 23.5 24.0 GB view
8k 783.9 22.7 25.1 GB view
16k 673.2 21.1 26.6 GB view
32k 617.4 19.9 29.6 GB view
64k 530.7 17.9 35.6 GB current
128k 400.1 15.1 48.0 GB view
Batching Results
Batch Size TG tok/s Speedup
23.8 1.00×
36.9 1.55×
42.7 1.79×
84.5 3.55×