← Back to community benchmarks

Qwen3.6-27B-oQ4-mtp

M4 Max (32c) · 36 GB · 4bit · 2026-05-11
Performance
16k
tokens
192.7
PP tok/s
27.6
TG tok/s
85027
TTFT (ms)
20.7
Peak mem (GB)
Hardware
Chip M4 Max (32c)
Memory 36 GB
GPU Cores 32
Software
oMLX v0.3.9.dev1
macOS macOS 26.5
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 193.0 32.8 16.8 GB view
4k 200.4 31.3 18.2 GB view
8k 198.5 30.1 19.2 GB view
16k 192.7 27.6 20.7 GB current
Batching Results
Batch Size TG tok/s Speedup
32.8 1.00×
39.7 1.21×
45.6 1.39×