← Back to community benchmarks

Qwen3.5-9B-OptiQ

M4 (8c) · 16 GB · 4bit · 2026-03-19
Performance
4k
tokens
166.3
PP tok/s
18.8
TG tok/s
24623
TTFT (ms)
7.4
Peak mem (GB)
Hardware
Chip M4 (8c)
Memory 16 GB
GPU Cores 8
Software
oMLX v0.2.18
macOS macOS 26.2
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 162.7 19.2 6.7 GB view
4k 166.3 18.8 7.4 GB current
Batching Results
Batch Size TG tok/s Speedup
19.2 1.00×
35.5 1.85×
37.6 1.96×