← Back to community benchmarks

Qwen3.6-27B-oQ4-mtp

M4 Max (40c) · 64 GB · 4bit · 2026-05-20
Performance
1k
tokens
229.4
PP tok/s
28.0
TG tok/s
4463
TTFT (ms)
16.7
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.3.9rc1
macOS macOS 26.3
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 229.4 28.0 16.7 GB current
4k 182.7 29.7 18.2 GB view
8k 182.8 26.8 19.2 GB view
Batching Results
Batch Size TG tok/s Speedup
28.0 1.00×
34.0 1.21×
38.7 1.38×