← Back to community benchmarks

Qwen3.6-27B-oQ4-mtp

M5 (10c) · 32 GB · 4bit · 2026-05-18
Performance
8k
tokens
205.0
PP tok/s
5.7
TG tok/s
39952
TTFT (ms)
18.8
Peak mem (GB)
Hardware
Chip M5 (10c)
Memory 32 GB
GPU Cores 10
Software
oMLX v0.3.8
macOS macOS 26.5
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 215.7 7.6 16.4 GB view
4k 219.0 6.3 17.8 GB view
8k 205.0 5.7 18.8 GB current
Batching Results
Batch Size TG tok/s Speedup
7.6 1.00×
149.0 19.61×
14.1 1.86×