← Back to community benchmarks

Qwen3.6-27B-MTPLX-Optimized-Speed

M1 Max (24c) · 64 GB · 4bit · 2026-05-23
Performance
16k
tokens
62.0
PP tok/s
11.2
TG tok/s
264200
TTFT (ms)
19.8
Peak mem (GB)
Hardware
Chip M1 Max (24c)
Memory 64 GB
GPU Cores 24
Software
oMLX v0.3.9
macOS macOS 26.4
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 65.6 12.9 15.8 GB view
4k 65.3 12.2 17.3 GB view
8k 64.8 11.6 18.3 GB view
16k 62.0 11.2 19.8 GB current
32k 60.2 10.3 22.8 GB view
Batching Results
Batch Size TG tok/s Speedup
12.9 1.00×
15.0 1.16×
16.6 1.29×