← Back to community benchmarks

Qwen3.6-35B-A3B-UD

M4 Pro (16c) · 48 GB · 4bit · 2026-05-15
Performance
1k
tokens
607.9
PP tok/s
64.2
TG tok/s
1684
TTFT (ms)
20.4
Peak mem (GB)
Hardware
Chip M4 Pro (16c)
Memory 48 GB
GPU Cores 16
Software
oMLX v0.3.9.dev2
macOS macOS 26.4.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 607.9 64.2 20.4 GB current
4k 741.7 60.8 21.2 GB view
8k 725.6 58.3 21.7 GB view
16k 674.0 54.0 22.4 GB view
32k 581.8 46.3 23.9 GB view
Batching Results
Batch Size TG tok/s Speedup
64.2 1.00×
99.1 1.54×
118.8 1.85×