← Back to community benchmarks

Qwen3.5-35B-A3B

M5 Pro (20c) · 64 GB · 4bit · 2026-03-16
Performance
4k
tokens
2,095
PP tok/s
94.9
TG tok/s
1955
TTFT (ms)
20.2
Peak mem (GB)
Hardware
Chip M5 Pro (20c)
Memory 64 GB
GPU Cores 20
Software
oMLX v0.2.12
macOS macOS 26.3.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,599 98.4 20.1 GB view
4k 2,095 94.9 20.2 GB current
8k 2,118 90.3 20.4 GB view
16k 1,981 76.0 20.8 GB view
32k 1,703 62.3 21.6 GB view
64k 1,278 41.6 23.3 GB view
128k 832.6 15.5 26.7 GB view
195k 604.5 10.6 30.3 GB view
Batching Results
Batch Size TG tok/s Speedup
98.4 1.00×
155.3 1.58×
211.2 2.15×
269.1 2.73×