← Back to community benchmarks

Qwen3.6-27B-Claude-4.6-OS-mxfp8

M5 Max (40c) · 128 GB · 8bit · 2026-04-29
Performance
16k
tokens
231.6
PP tok/s
17.2
TG tok/s
70744
TTFT (ms)
30.9
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.8rc1
macOS macOS 26.4.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 241.4 18.8 27.6 GB view
4k 254.5 19.1 29.0 GB view
8k 240.9 18.5 29.6 GB view
16k 231.6 17.2 30.9 GB current
32k 194.7 14.8 33.4 GB view
Batching Results
Batch Size TG tok/s Speedup
18.8 1.00×
27.1 1.44×