← Back to community benchmarks

Qwen3.6-27B-oQ6-fp16-mtp

M1 Max (32c) · 64 GB · 6bit · 2026-05-17
User commentwith MTP
Performance
16k
tokens
75.2
PP tok/s
7.8
TG tok/s
217868
TTFT (ms)
26.9
Peak mem (GB)
Hardware
Chip M1 Max (32c)
Memory 64 GB
GPU Cores 32
Software
oMLX v0.3.9.dev1
macOS macOS 15.6.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 84.5 11.9 23.0 GB view
4k 89.1 10.4 24.4 GB view
8k 79.7 9.6 25.4 GB view
16k 75.2 7.8 26.9 GB current