← Back to community benchmarks

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

M1 Max (32c) · 64 GB · 4bit · 2026-05-17
Performance
8k
tokens
88.2
PP tok/s
17.4
TG tok/s
92868
TTFT (ms)
18.3
Peak mem (GB)
Hardware
Chip M1 Max (32c)
Memory 64 GB
GPU Cores 32
Software
oMLX v0.3.8
macOS macOS 26.4.1
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 86.5 18.9 15.8 GB view
4k 88.9 18.0 17.3 GB view
8k 88.2 17.4 18.3 GB current
Batching Results
Batch Size TG tok/s Speedup
18.9 1.00×
22.1 1.17×
22.1 1.17×
18.2 0.96×