← Back to community benchmarks

Qwen3.6-35B-A3B-UD

M4 Max (40c) · 48 GB · 4bit · 2026-05-18
Performance
1k
tokens
966.7
PP tok/s
89.4
TG tok/s
1059
TTFT (ms)
20.4
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 48 GB
GPU Cores 40
Software
oMLX v0.3.9.dev1
macOS macOS 26.4.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 966.7 89.4 20.4 GB current
4k 1,599 80.5 21.2 GB view
Batching Results
Batch Size TG tok/s Speedup
89.4 1.00×
132.5 1.48×
198.3 2.22×