← Back to community benchmarks

Qwen3.6-35B-A3B-UD

M5 Max (40c) · 128 GB · 4bit · 2026-04-26
Performance
195k
tokens
1,020
PP tok/s
34.4
TG tok/s
196130
TTFT (ms)
37.2
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.6
macOS macOS 26.4
Context 200,000
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 2,187 105.6 20.4 GB view
4k 3,560 102.6 21.2 GB view
128k 1,466 44.3 31.6 GB view
195k 1,020 34.4 37.2 GB current
Batching Results
Batch Size TG tok/s Speedup
105.6 1.00×
188.4 1.78×
284.1 2.69×