← Back to community benchmarks

Qwen3.6-27B-oQ8-mtp

M4 Max (40c) · 128 GB · 8bit · 2026-05-14
Performance
4k
tokens
206.7
PP tok/s
22.5
TG tok/s
19811
TTFT (ms)
30.3
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.9.dev2
macOS macOS 15.7
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 235.5 22.8 28.8 GB view
4k 206.7 22.5 30.3 GB current