← Back to community benchmarks

Qwen3.6-27B-oQ8-mtp

M4 Max (40c) · 64 GB · 8bit · 2026-05-19
User commentQwen3.6-27B-oQ8 model without MTP Optimizations
Performance
16k
tokens
167.3
PP tok/s
10.6
TG tok/s
97937
TTFT (ms)
32.3
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.3.9rc1
macOS macOS 26.4.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 233.6 16.2 28.3 GB view
4k 200.6 15.0 29.8 GB view
8k 184.7 15.0 30.8 GB view
16k 167.3 10.6 32.3 GB current
Batching Results
Batch Size TG tok/s Speedup
16.2 1.00×
19.7 1.22×
26.5 1.64×