← Back to community benchmarks

Qwen3.6-27B-oQ8-mtp

M1 Max (32c) · 64 GB · 8bit · 2026-06-04
Performance
16k
tokens
81.1
PP tok/s
8.2
TG tok/s
201983
TTFT (ms)
32.1
Peak mem (GB)
Hardware
Chip M1 Max (32c)
Memory 64 GB
GPU Cores 32
Software
oMLX v0.4.1
macOS macOS 26.5
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
4k 85.7 10.0 29.1 GB view
16k 81.1 8.2 32.1 GB current