← Back to community benchmarks

Qwen3.5-9B-OptiQ

M4 Max (40c) · 48 GB · 4bit · 2026-05-03
Performance
4k
tokens
564.5
PP tok/s
77.8
TG tok/s
7255
TTFT (ms)
7.5
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 48 GB
GPU Cores 40
Software
oMLX v0.3.8
macOS macOS 26.4.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 657.0 79.4 6.8 GB view
4k 564.5 77.8 7.5 GB current
Batching Results
Batch Size TG tok/s Speedup
79.4 1.00×
120.0 1.51×
131.8 1.66×