← Back to community benchmarks

Qwen3.5-9B

M3 Max (40c) · 64 GB · 4bit · 2026-03-11
Performance
1k
tokens
570.7
PP tok/s
57.2
TG tok/s
1794
TTFT (ms)
6.7
Peak mem (GB)
Hardware
Chip M3 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.2.7
macOS macOS 26.3
Context 1,024
Batching Results
Batch Size TG tok/s Speedup
1× 57.2 1.00×
2× 82.3 1.44×
4× 89.4 1.56×
8× 95.3 1.67×