← Back to community benchmarks

Qwen3.6-35B-A3B

M3 Max (40c) · 48 GB · 4bit · 2026-04-24
Performance
4k
tokens
1,440
PP tok/s
89.3
TG tok/s
2845
TTFT (ms)
20.0
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 1,019 93.0 19.2 GB view
4k 1,440 89.3 20.0 GB current
Batching Results
Batch Size TG tok/s Speedup
1× 93.0 1.00×
2× 155.0 1.67×
4× 229.2 2.46×