← Back to community benchmarks

Qwen3.6-27B-oQ8-mtp

M5 Max (40c) · 128 GB · 8bit · 2026-05-15
Performance
128k
tokens
332.1
PP tok/s
9.9
TG tok/s
394627
TTFT (ms)
49.6
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.9.dev2
macOS macOS 26.4
Context 131,072
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
128k 332.1 9.9 49.6 GB current
195k 215.1 7.8 68.4 GB view