← Back to community benchmarks

Qwen3.6-27B-oQ4-mtp

M2 Max (30c) · 64 GB · 4bit · 2026-06-03
Performance
4k
tokens
89.7
PP tok/s
17.1
TG tok/s
45657
TTFT (ms)
18.1
Peak mem (GB)
Hardware
Chip M2 Max (30c)
Memory 64 GB
GPU Cores 30
Software
oMLX v0.4.1
macOS macOS 26.3.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
4k 89.7 17.1 18.1 GB current
16k 89.5 16.4 20.5 GB view