← Back to community benchmarks

Qwen3.6-27B-oQ4-mtp

M4 Max (32c) · 36 GB · 4bit · 2026-05-09
Performance
1k
tokens
186.2
PP tok/s
30.5
TG tok/s
5500
TTFT (ms)
16.8
Peak mem (GB)
Hardware
Chip M4 Max (32c)
Memory 36 GB
GPU Cores 32
Software
oMLX v0.3.9.dev1
macOS macOS 26.4
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 186.2 30.5 16.8 GB current
4k 160.1 30.0 18.2 GB view
Batching Results
Batch Size TG tok/s Speedup
30.5 1.00×
32.5 1.07×
32.7 1.07×