← Back to community benchmarks

Qwen3.6-27B-oQ4-mtp

M5 Max (40c) · 64 GB · 4bit · 2026-05-18
Performance
1k
tokens
790.2
PP tok/s
47.6
TG tok/s
1296
TTFT (ms)
16.7
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.3.9.dev2
macOS macOS 26.4.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 790.2 47.6 16.7 GB current
4k 810.1 44.7 18.2 GB view
8k 723.8 40.5 19.2 GB view
16k 688.3 37.3 20.7 GB view
Batching Results
Batch Size TG tok/s Speedup
47.6 1.00×
49.5 1.04×
60.6 1.27×