← Back to community benchmarks

unsloth--Qwen3.6-27B

M5 Max (40c) · 128 GB · 8bit · 2026-07-19
Performance
32k
tokens
450.9
PP tok/s
13.5
TG tok/s
72669
TTFT (ms)
41.3
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.5.1
macOS macOS 26.5.2
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 833.4 12.5 33.0 GB view
4k 381.9 12.6 35.6 GB view
8k 398.1 12.2 36.5 GB view
16k 457.4 14.1 38.0 GB view
32k 450.9 13.5 41.3 GB current
64k 368.5 12.2 47.3 GB view
128k 259.2 10.1 59.6 GB view
195k 208.0 8.9 73.5 GB view
Batching Results
Batch Size TG tok/s Speedup
12.5 1.00×
16.5 1.32×
29.6 2.37×
35.0 2.80×