← Back to community benchmarks

Qwen3.5-9B

M4 (8c) · 16 GB · 4bit · 2026-03-15
Performance
1k
tokens
169.3
PP tok/s
21.1
TG tok/s
6048
TTFT (ms)
6.5
Peak mem (GB)
Hardware
Chip M4 (8c)
Memory 16 GB
GPU Cores 8
Software
oMLX v0.2.11
macOS macOS 15.7.3
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 169.3 21.1 6.5 GB current
4k 169.6 20.5 6.8 GB view
Batching Results
Batch Size TG tok/s Speedup
21.1 1.00×
39.2 1.86×
40.7 1.93×