← Back to community benchmarks

Qwen3.6-27B-oQ4-mtp

M3 Max (40c) · 128 GB · 4bit · 2026-05-20
Performance
1k
tokens
207.6
PP tok/s
21.8
TG tok/s
4932
TTFT (ms)
16.4
Peak mem (GB)
Hardware
Chip M3 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.9rc1
macOS macOS 15.7.5
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 207.6 21.8 16.4 GB current
4k 195.5 19.2 17.9 GB view
16k 180.3 18.1 20.1 GB view
Batching Results
Batch Size TG tok/s Speedup
21.8 1.00×
28.7 1.32×
37.0 1.70×
37.1 1.70×