← Back to community benchmarks

Qwen3.5-9B

M4 Max (40c) · 64 GB · 4bit · 2026-03-10
Performance
1k
tokens
872.6
PP tok/s
87.6
TG tok/s
1174
TTFT (ms)
6.7
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.2.6
macOS macOS 26.2
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 872.6 87.6 6.7 GB current
4k 880.1 84.8 7.0 GB view
Batching Results
Batch Size TG tok/s Speedup
87.6 1.00×
162.7 1.86×
192.6 2.20×
206.1 2.35×