← Back to community benchmarks

Qwen3.6-27B-oQ8-mtp

M1 Max (32c) · 64 GB · 8bit · 2026-05-10
Performance
1k
tokens
87.5
PP tok/s
11.6
TG tok/s
11706
TTFT (ms)
28.3
Peak mem (GB)
Hardware
Chip M1 Max (32c)
Memory 64 GB
GPU Cores 32
Software
oMLX v0.3.9.dev1
macOS macOS 15.4.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 87.5 11.6 28.3 GB current
4k 89.7 11.4 29.8 GB view
Batching Results
Batch Size TG tok/s Speedup
1× 11.6 1.00×
2× 20.0 1.72×
4× 22.2 1.91×