← Back to community benchmarks

Qwen3.6-27B-oQ8-fp16-mtp

M5 Max (40c) · 64 GB · 8bit · 2026-05-16
Performance
4k
tokens
716.4
PP tok/s
29.1
TG tok/s
5717
TTFT (ms)
30.3
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.3.9.dev2
macOS macOS 26.4.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 720.9 29.5 28.8 GB view
4k 716.4 29.1 30.3 GB current
8k 667.0 26.5 31.3 GB view
Batching Results
Batch Size TG tok/s Speedup
29.5 1.00×
32.9 1.12×
43.4 1.47×