← Back to community benchmarks

Qwen3.6-27B-oQ4-mtp

M2 Max (30c) · 32 GB · 4bit · 2026-06-04
Performance
4k
tokens
88.4
PP tok/s
16.2
TG tok/s
46340
TTFT (ms)
17.7
Peak mem (GB)
Hardware
Chip M2 Max (30c)
Memory 32 GB
GPU Cores 30
Software
oMLX v0.4.0
macOS macOS 14.6
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 86.8 12.8 16.5 GB view
4k 88.4 16.2 17.7 GB current
8k 90.0 16.1 18.8 GB view
16k 88.4 15.2 20.0 GB view
Batching Results
Batch Size TG tok/s Speedup
12.8 1.00×
18.2 1.42×
36.6 2.86×