← Back to community benchmarks

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

M4 Max (40c) · 128 GB · 4bit · 2026-05-19
Performance
16k
tokens
217.3
PP tok/s
35.9
TG tok/s
75383
TTFT (ms)
20.4
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 128 GB
GPU Cores 40
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
1k 255.5 34.4 16.7 GB view
4k 246.1 39.7 18.2 GB view
16k 217.3 35.9 20.4 GB current
Batching Results
Batch Size TG tok/s Speedup
34.4 1.00×
48.3 1.40×
54.1 1.57×