← Back to community benchmarks

Qwen3.6-35B-A3B

M4 Max (40c) · 128 GB · 8bit · 2026-04-18
Performance
8k
tokens
1,701
PP tok/s
80.3
TG tok/s
4817
TTFT (ms)
36.5
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.6
macOS macOS 26.3
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,348 86.5 35.4 GB view
4k 1,706 83.4 36.2 GB view
8k 1,701 80.3 36.5 GB current
Batching Results
Batch Size TG tok/s Speedup
86.5 1.00×
139.0 1.61×