← Back to community benchmarks

community--Qwen3.6-27B-OptiQ

M5 Max (40c) · 64 GB · 4bit · 2026-06-04
Performance
4k
tokens
872.9
PP tok/s
26.2
TG tok/s
4693
TTFT (ms)
20.6
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 746.1 26.6 19.2 GB view
4k 872.9 26.2 20.6 GB current
Batching Results
Batch Size TG tok/s Speedup
26.6 1.00×
49.5 1.86×
66.7 2.51×