← Back to community benchmarks

Qwen3.6-27B-oQ8-mtp

M4 Max (40c) · 64 GB · 8bit · 2026-05-14
Performance
64k
tokens
201.6
PP tok/s
19.0
TG tok/s
325069
TTFT (ms)
39.7
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.3.9.dev2
macOS macOS 26.0.1
Context 65,536