← Back to community benchmarks

Qwen3.5-35B-A3B

M4 Pro (16c) · 48 GB · 4bit · 2026-04-12
Performance
32k
tokens
577.2
PP tok/s
48.1
TG tok/s
56774
TTFT (ms)
22.3
Peak mem (GB)
Hardware
Chip M4 Pro (16c)
Memory 48 GB
GPU Cores 16
Software
oMLX v0.3.4
macOS macOS 15.7.4
Context 32,768