← Back to community benchmarks

Qwen3.6-35B-A3B-4bit-DWQ

M3 Max (30c) · 96 GB · 8bit · 2026-04-17
Performance
4k
tokens
1,130
PP tok/s
65.8
TG tok/s
3625
TTFT (ms)
21.1
Peak mem (GB)
Hardware
Chip M3 Max (30c)
Memory 96 GB
GPU Cores 30
Software
oMLX v0.3.5
macOS macOS 26.4.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 929.1 68.5 20.3 GB view
4k 1,130 65.8 21.1 GB current