← Back to community benchmarks

Qwen3.6-27B-oQ8-mtp

M4 Max (40c) · 128 GB · 8bit · 2026-05-07
Performance
1k
tokens
185.0
PP tok/s
19.5
TG tok/s
5536
TTFT (ms)
28.8
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.9.dev1
macOS macOS 26.5
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 185.0 19.5 28.8 GB current
4k 172.9 19.2 30.3 GB view