← Back to community benchmarks

Qwen3.6-35B-A3B

M4 Pro (16c) · 48 GB · 4bit · 2026-07-24
Performance
64k
tokens
335.4
PP tok/s
25.7
TG tok/s
195376
TTFT (ms)
25.0
Peak mem (GB)
Hardware
Chip M4 Pro (16c)
Memory 48 GB
GPU Cores 16
Software
oMLX v0.4.3
macOS macOS 27.0
Context 65,536