← Back to community benchmarks

Qwen3___5-9B

M3 (10c) · 16 GB · 4bit · 2026-03-10
Performance
4k
tokens
184.6
PP tok/s
18.3
TG tok/s
22183
TTFT (ms)
6.8
Peak mem (GB)
Hardware
Chip M3 (10c)
Memory 16 GB
GPU Cores 10
Software
oMLX v0.2.7
macOS macOS 15.7.4
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 187.2 19.1 6.5 GB view
4k 184.6 18.3 6.8 GB current
Batching Results
Batch Size TG tok/s Speedup
19.1 1.00×
35.9 1.88×
37.8 1.98×