← Back to community benchmarks

Qwen3.5-9B-OptiQ

M1 (8c) · 16 GB · 4bit · 2026-03-10
Performance
1k
tokens
100.7
PP tok/s
8.4
TG tok/s
10168
TTFT (ms)
7.6
Peak mem (GB)
Hardware
Chip M1 (8c)
Memory 16 GB
GPU Cores 8
Software
oMLX v0.2.6
macOS macOS 15.1.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 100.7 8.4 7.6 GB current
4k 103.8 8.1 8.1 GB view
Batching Results
Batch Size TG tok/s Speedup
1× 8.4 1.00×
2× 16.3 1.94×
4× 21.3 2.54×