← Back to community benchmarks

Qwen3.6-27B-oQ4-mtp

M1 Max (32c) · 64 GB · 4bit · 2026-05-13
Performance
8k
tokens
89.6
PP tok/s
16.8
TG tok/s
91426
TTFT (ms)
19.2
Peak mem (GB)
Hardware
Chip M1 Max (32c)
Memory 64 GB
GPU Cores 32
Software
oMLX v0.3.9.dev2
macOS macOS 26.4.1
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 88.2 17.3 16.8 GB view
8k 89.6 16.8 19.2 GB current
16k 88.0 16.1 20.7 GB view
Batching Results
Batch Size TG tok/s Speedup
1× 17.3 1.00×
2× 21.2 1.23×