← Back to community benchmarks

Qwen3.6-27B-oQ8-mtp

M5 Max (40c) · 128 GB · 8bit · 2026-06-15
Performance
4k
tokens
861.3
PP tok/s
18.5
TG tok/s
4756
TTFT (ms)
29.8
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.4.4rc1
macOS macOS 26.5.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 721.8 18.7 28.3 GB view
4k 861.3 18.5 29.8 GB current
8k 826.1 18.2 30.8 GB view
16k 718.6 17.6 32.3 GB view