← Back to community benchmarks

Qwen3.5-9B

M4 (8c) · 16 GB · 4bit · 2026-03-09
Performance
4k
tokens
169.8
PP tok/s
20.6
TG tok/s
24125
TTFT (ms)
6.8
Peak mem (GB)
Hardware
Chip M4 (8c)
Memory 16 GB
GPU Cores 8
Software
oMLX v0.2.6
macOS macOS 26.3.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 169.8 21.2 6.5 GB view
4k 169.8 20.6 6.8 GB current
Batching Results
Batch Size TG tok/s Speedup
21.2 1.00×
36.7 1.73×
38.0 1.79×