← Back to community benchmarks

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

M3 Ultra (80c) · 256 GB · 8bit · 2026-04-18
Performance
1k
tokens
1,760
PP tok/s
96.4
TG tok/s
582
TTFT (ms)
20.3
Peak mem (GB)
Hardware
Chip M3 Ultra (80c)
Memory 256 GB
GPU Cores 80
Software
oMLX v0.3.6
macOS macOS 26.4.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,760 96.4 20.3 GB current
4k 2,605 89.4 21.1 GB view
8k 2,695 87.0 21.5 GB view
16k 2,568 80.2 22.1 GB view
32k 2,223 68.7 23.4 GB view
Batching Results
Batch Size TG tok/s Speedup
96.4 1.00×
163.5 1.70×