← Back to community benchmarks

Qwen3.5-35B-A3B

M5 Pro (20c) · 64 GB · 8bit · 2026-03-27
Performance
8k
tokens
2,218
PP tok/s
45.6
TG tok/s
3693
TTFT (ms)
37.5
Peak mem (GB)
Hardware
Chip M5 Pro (20c)
Memory 64 GB
GPU Cores 20
Software
oMLX v0.2.22
macOS macOS 26.3.1
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,769 50.9 36.2 GB view
4k 2,224 48.2 37.1 GB view
8k 2,218 45.6 37.5 GB current
16k 2,053 40.9 38.2 GB view
32k 1,748 31.5 39.5 GB view
64k 1,254 23.0 42.1 GB view
128k 804.4 14.6 47.5 GB view