← Back to community benchmarks

Qwen3.5-9B

M4 (10c) · 24 GB · 4bit · 2026-05-12
Performance
4k
tokens
78.3
PP tok/s
7.7
TG tok/s
52302
TTFT (ms)
6.3
Peak mem (GB)
Hardware
Chip M4 (10c)
Memory 24 GB
GPU Cores 10
Software
oMLX v0.3.9.dev1
macOS macOS 15.7.4
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 80.1 9.1 5.7 GB view
4k 78.3 7.7 6.3 GB current
Batching Results
Batch Size TG tok/s Speedup
9.1 1.00×
13.5 1.48×
14.4 1.58×