← Back to community benchmarks

Qwen3.6-27B-oQ4-mtp

M3 Max (30c) · 36 GB · 4bit · 2026-05-08
Performance
32k
tokens
142.2
PP tok/s
18.7
TG tok/s
230451
TTFT (ms)
23.7
Peak mem (GB)
Hardware
Chip M3 Max (30c)
Memory 36 GB
GPU Cores 30
Software
oMLX v0.3.9.dev1
macOS macOS 26.4.1
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 159.2 25.9 16.8 GB view
4k 159.3 24.2 18.2 GB view
8k 146.5 24.1 19.2 GB view
16k 148.9 21.6 20.7 GB view
32k 142.2 18.7 23.7 GB current
Batching Results
Batch Size TG tok/s Speedup
25.9 1.00×
27.1 1.05×
31.5 1.22×