← Back to community benchmarks

Qwen3.6-35B-A3B-UD

M5 Pro (20c) · 48 GB · 4bit · 2026-04-23
Performance
8k
tokens
2,247
PP tok/s
69.0
TG tok/s
3645
TTFT (ms)
21.5
Peak mem (GB)
Hardware
Chip M5 Pro (20c)
Memory 48 GB
GPU Cores 20
Software
oMLX v0.3.7
macOS macOS 26.3
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,489 75.6 20.4 GB view
4k 2,168 72.8 21.2 GB view
8k 2,247 69.0 21.5 GB current
Batching Results
Batch Size TG tok/s Speedup
75.6 1.00×
118.8 1.57×
162.8 2.15×
201.1 2.66×