← Back to community benchmarks

Qwen3.6-27B-oQ4-mtp

M2 Ultra (60c) · 128 GB · 4bit · 2026-05-11
Performance
4k
tokens
179.0
PP tok/s
30.5
TG tok/s
22888
TTFT (ms)
18.2
Peak mem (GB)
Hardware
Chip M2 Ultra (60c)
Memory 128 GB
GPU Cores 60
Software
oMLX v0.3.9.dev1
macOS macOS 15.6.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 171.8 32.1 16.8 GB view
4k 179.0 30.5 18.2 GB current
8k 178.5 29.0 19.2 GB view
Batching Results
Batch Size TG tok/s Speedup
32.1 1.00×
38.9 1.21×
43.3 1.35×