← Back to community benchmarks

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

M4 Max (32c) · 36 GB · 4bit · 2026-06-03
Performance
1k
tokens
166.8
PP tok/s
28.0
TG tok/s
6138
TTFT (ms)
16.3
Peak mem (GB)
Hardware
Chip M4 Max (32c)
Memory 36 GB
GPU Cores 32
Software
oMLX v0.4.1
macOS macOS 26.5.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 166.8 28.0 16.3 GB current
4k 177.9 26.9 17.5 GB view
Batching Results
Batch Size TG tok/s Speedup
28.0 1.00×
30.8 1.10×
60.1 2.15×