← Back to community benchmarks

Qwen3.6-27B-oQ8-mtp

M5 Max (40c) · 128 GB · 8bit · 2026-05-14
Performance
195k
tokens
337.6
PP tok/s
12.1
TG tok/s
592406
TTFT (ms)
62.4
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 200,000
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
32k 698.0 16.5 34.2 GB view
195k 337.6 12.1 62.4 GB current