← Back to community benchmarks

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

M1 Max (24c) · 64 GB · 6bit · 2026-05-23
Performance
32k
tokens
81.0
PP tok/s
8.4
TG tok/s
404456
TTFT (ms)
29.4
Peak mem (GB)
Hardware
Chip M1 Max (24c)
Memory 64 GB
GPU Cores 24
Software
oMLX v0.3.9
macOS macOS 26.4
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 98.7 10.0 22.4 GB view
4k 87.7 9.3 23.8 GB view
8k 86.3 9.1 24.9 GB view
16k 83.2 8.8 26.4 GB view
32k 81.0 8.4 29.4 GB current
Batching Results
Batch Size TG tok/s Speedup
10.0 1.00×
11.7 1.17×
13.3 1.33×