← Back to community benchmarks

Qwen3.6-27B-oQ4-fp16-mtp

M1 Max (32c) · 32 GB · 4bit · 2026-05-13
Performance
16k
tokens
147.1
PP tok/s
20.6
TG tok/s
111413
TTFT (ms)
20.7
Peak mem (GB)
Hardware
Chip M1 Max (32c)
Memory 32 GB
GPU Cores 32
Software
oMLX v0.3.9.dev2
macOS macOS 26.4.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
8k 76.3 21.7 18.8 GB view
16k 147.1 20.6 20.7 GB current