← Back to community benchmarks

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

M5 Max (40c) · 128 GB · 8bit · 2026-05-03
Performance
1k
tokens
2,258
PP tok/s
118.0
TG tok/s
454
TTFT (ms)
20.3
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.8
macOS macOS 26.4.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 2,258 118.0 20.3 GB current
4k 3,825 113.2 21.1 GB view
Batching Results
Batch Size TG tok/s Speedup
118.0 1.00×
192.3 1.63×
287.9 2.44×