← Back to community benchmarks

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

M3 Max (40c) · 128 GB · 8bit · 2026-04-27
Performance
16k
tokens
2,693
PP tok/s
32.1
TG tok/s
6085
TTFT (ms)
23.0
Peak mem (GB)
Hardware
Chip M3 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.7rc2
macOS macOS 26.4.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,140 80.0 20.7 GB view
4k 1,410 77.0 21.5 GB view
16k 2,693 32.1 23.0 GB current
Batching Results
Batch Size TG tok/s Speedup
80.0 1.00×
128.0 1.60×