← Back to community benchmarks

Qwen3.6-35B-A3B

M4 Pro (20c) · 64 GB · 4bit · 2026-04-17
User commentmlx-community/Qwen3.6-35B-A3B-4bit
Performance
64k
tokens
515.7
PP tok/s
35.2
TG tok/s
127090
TTFT (ms)
25.0
Peak mem (GB)
Hardware
Chip M4 Pro (20c)
Memory 64 GB
GPU Cores 20
Software
oMLX v0.3.6
macOS macOS 26.4.1
Context 65,536