← Back to community benchmarks

Qwen3.5-9B

M4 (8c) · 16 GB · 4bit · 2026-04-17
Performance
4k
tokens
162.6
PP tok/s
18.8
TG tok/s
25194
TTFT (ms)
6.3
Peak mem (GB)
Hardware
Chip M4 (8c)
Memory 16 GB
GPU Cores 8
Software
oMLX v0.3.6
macOS macOS 26.2
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 156.7 18.4 5.7 GB view
4k 162.6 18.8 6.3 GB current
Batching Results
Batch Size TG tok/s Speedup
18.4 1.00×
34.9 1.90×
37.6 2.04×