← Back to community benchmarks

Qwen3.6-27B-oQ4-mtp

M5 (10c) · 32 GB · 4bit · 2026-05-20
Performance
4k
tokens
194.6
PP tok/s
13.2
TG tok/s
21052
TTFT (ms)
18.1
Peak mem (GB)
Hardware
Chip M5 (10c)
Memory 32 GB
GPU Cores 10
Software
oMLX v0.3.9rc1
macOS macOS 26.4
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 190.3 13.4 16.6 GB view
4k 194.6 13.2 18.1 GB current
8k 178.5 11.9 19.1 GB view
16k 143.3 9.0 20.6 GB view
Batching Results
Batch Size TG tok/s Speedup
13.4 1.00×
18.3 1.37×
33.6 2.51×