← Back to community benchmarks

Qwen3.6-27B-oQ8-mtp

M5 Max (40c) · 128 GB · 8bit · 2026-05-14
Performance
16k
tokens
805.1
PP tok/s
27.1
TG tok/s
20350
TTFT (ms)
32.1
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 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
16k 805.1 27.1 32.1 GB current
32k 660.2 25.9 35.8 GB view