← Back to community benchmarks

ThinkingCap-Qwen3.6-27B-OptiQ

M5 Pro (20c) · 48 GB · 4bit · 2026-07-19
Performance
64k
tokens
242.5
PP tok/s
11.3
TG tok/s
270280
TTFT (ms)
25.3
Peak mem (GB)
Hardware
Chip M5 Pro (20c)
Memory 48 GB
GPU Cores 20
Software
oMLX v0.4.4
macOS macOS 26.5.2
Context 65,536
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 400.0 14.2 19.2 GB view
4k 439.8 14.2 20.6 GB view
8k 419.5 13.9 21.7 GB view
16k 409.1 13.4 23.2 GB view
32k 234.4 12.7 25.0 GB view
64k 242.5 11.3 25.3 GB current
Batching Results
Batch Size TG tok/s Speedup
14.2 1.00×
25.2 1.77×
35.9 2.53×