← Back to community benchmarks

Qwen3.6-27B-mxfp8

M5 Max (40c) · 128 GB · 8bit · 2026-04-25
Performance
8k
tokens
812.5
PP tok/s
18.6
TG tok/s
10083
TTFT (ms)
29.6
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.7
macOS macOS 26.4.1
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 708.6 19.3 27.6 GB view
4k 838.2 19.0 29.0 GB view
8k 812.5 18.6 29.6 GB current
16k 722.1 17.8 30.9 GB view
32k 657.1 16.7 33.4 GB view
Batching Results
Batch Size TG tok/s Speedup
19.3 1.00×
33.6 1.74×
41.6 2.16×