← Back to community benchmarks

unsloth--Qwen3.6-27B

M5 Max (40c) · 128 GB · 8bit · 2026-07-19
Performance
8k
tokens
398.1
PP tok/s
12.2
TG tok/s
20577
TTFT (ms)
36.5
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 8,192
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 current
16k 457.4 14.1 38.0 GB view
32k 450.9 13.5 41.3 GB view
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×