← Back to community benchmarks

Qwen3.6-27B-oQ6

M5 Max (40c) · 128 GB · 6bit · 2026-05-19
Performance
16k
tokens
539.2
PP tok/s
17.0
TG tok/s
30387
TTFT (ms)
26.6
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.9rc1
macOS macOS 26.5
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 411.4 17.6 22.6 GB view
4k 522.2 17.9 24.0 GB view
8k 554.1 17.9 25.1 GB view
16k 539.2 17.0 26.6 GB current
32k 478.0 13.7 29.6 GB view
Batching Results
Batch Size TG tok/s Speedup
17.6 1.00×
22.2 1.26×
26.7 1.52×