← Back to community benchmarks

Qwen3.6-27B-oQ4-mtp

M1 Max (32c) · 64 GB · 4bit · 2026-05-23
Performance
8k
tokens
74.4
PP tok/s
12.6
TG tok/s
110154
TTFT (ms)
18.9
Peak mem (GB)
Hardware
Chip M1 Max (32c)
Memory 64 GB
GPU Cores 32
Software
oMLX v0.3.9
macOS macOS 26.5
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
4k 79.4 13.3 17.9 GB view
8k 74.4 12.6 18.9 GB current
16k 73.3 11.8 20.4 GB view