← Back to community benchmarks

Qwen3.6-27B-oQ4-mtp

M5 Max (40c) · 64 GB · 4bit · 2026-06-04
Performance
4k
tokens
737.1
PP tok/s
42.1
TG tok/s
5557
TTFT (ms)
17.6
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.4.0
macOS macOS 26.5
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 699.7 44.4 16.8 GB view
4k 737.1 42.1 17.6 GB current
8k 701.6 39.8 19.2 GB view
16k 679.0 36.8 20.7 GB view
Batching Results
Batch Size TG tok/s Speedup
44.4 1.00×
46.5 1.05×
58.1 1.31×