← Back to community benchmarks

Qwen3.6-35B-A3B-PARO

M3 Ultra (60c) · 256 GB · 4bit · 2026-07-19
Performance
64k
tokens
1,236
PP tok/s
54.9
TG tok/s
53013
TTFT (ms)
20.5
Peak mem (GB)
Hardware
Chip M3 Ultra (60c)
Memory 256 GB
GPU Cores 60
Software
oMLX v0.5.2.dev1
macOS macOS 27.0
Context 65,536
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,823 69.3 18.6 GB view
4k 2,361 67.6 19.2 GB view
8k 2,309 67.6 19.3 GB view
16k 2,048 63.4 19.4 GB view
32k 1,682 59.8 19.8 GB view
64k 1,236 54.9 20.5 GB current
128k 808.6 44.9 22.1 GB view
195k 593.1 39.1 23.9 GB view
Batching Results
Batch Size TG tok/s Speedup
69.3 1.00×
108.2 1.56×