← Back to community benchmarks

Qwen3.6-27B-MXFP4-MTP

M5 Max (40c) · 128 GB · 4bit · 2026-05-16
Performance
8k
tokens
881.2
PP tok/s
33.9
TG tok/s
9296
TTFT (ms)
17.5
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.9.dev2
macOS macOS 26.5
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 809.7 35.6 15.1 GB view
4k 926.4 34.7 16.5 GB view
8k 881.2 33.9 17.5 GB current