← Back to community benchmarks

Qwen3.5-35B-A3B

M5 Pro (20c) · 48 GB · 4bit · 2026-03-29
Performance
16k
tokens
2,069
PP tok/s
63.6
TG tok/s
7919
TTFT (ms)
22.0
Peak mem (GB)
Hardware
Chip M5 Pro (20c)
Memory 48 GB
GPU Cores 20
Software
oMLX v0.2.24
macOS macOS 26.4
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
4k 2,052 73.0 21.0 GB view
16k 2,069 63.6 22.0 GB current
32k 1,787 50.6 23.4 GB view
64k 1,306 38.5 26.0 GB view