← Back to community benchmarks

Qwen3.6-35B-A3B

M3 Max (40c) · 48 GB · 8bit · 2026-04-25
Performance
4k
tokens
1,421
PP tok/s
69.1
TG tok/s
2883
TTFT (ms)
36.2
Peak mem (GB)
Hardware
Chip M3 Max (40c)
Memory 48 GB
GPU Cores 40
Software
oMLX v0.3.7
macOS macOS 26.3.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,089 71.6 35.4 GB view
4k 1,421 69.1 36.2 GB current
Batching Results
Batch Size TG tok/s Speedup
1× 71.6 1.00×
2× 115.3 1.61×
4× 164.5 2.30×