← Back to community benchmarks

Qwen3.6-27B-oQ4-mtp

M2 Ultra (60c) · 64 GB · 4bit · 2026-05-11
Performance
1k
tokens
174.8
PP tok/s
31.2
TG tok/s
5857
TTFT (ms)
17.3
Peak mem (GB)
Hardware
Chip M2 Ultra (60c)
Memory 64 GB
GPU Cores 60
Software
oMLX v0.3.9.dev1
macOS macOS 26.3.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 174.8 31.2 17.3 GB current
4k 181.8 30.1 18.8 GB view
Batching Results
Batch Size TG tok/s Speedup
1× 31.2 1.00×
2× 39.0 1.25×
4× 5.2 0.17×