← Back to community benchmarks

Qwen3.5-9B

M4 Max (32c) · 36 GB · unknown · 2026-03-11
Performance
4k
tokens
591.0
PP tok/s
4.3
TG tok/s
6931
TTFT (ms)
23.0
Peak mem (GB)
Hardware
Chip M4 Max (32c)
Memory 36 GB
GPU Cores 32
Software
oMLX v0.2.7
macOS macOS 15.7
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 487.6 4.4 22.8 GB view
4k 591.0 4.3 23.0 GB current
Batching Results
Batch Size TG tok/s Speedup
4.4 1.00×
8.0 1.82×
15.7 3.57×