← Back to community benchmarks

Qwen3.5-9B-OptiQ

M1 Max (24c) · 32 GB · 4bit · 2026-03-10
Performance
1k
tokens
308.5
PP tok/s
40.2
TG tok/s
3319
TTFT (ms)
7.8
Peak mem (GB)
Hardware
Chip M1 Max (24c)
Memory 32 GB
GPU Cores 24
Software
oMLX v0.2.6
macOS macOS 26.3
Context 1,024
Batching Results
Batch Size TG tok/s Speedup
1× 40.2 1.00×
2× 53.8 1.34×
4× 61.3 1.52×
8× 63.1 1.57×