← Back to community benchmarks

Qwen3.5-9B

M2 Pro (19c) · 32 GB · 8bit · 2026-03-13
Performance
4k
tokens
209.0
PP tok/s
20.0
TG tok/s
19594
TTFT (ms)
11.0
Peak mem (GB)
Hardware
Chip M2 Pro (19c)
Memory 32 GB
GPU Cores 19
Software
oMLX v0.2.10
macOS macOS 26.3
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 207.5 20.5 10.7 GB view
4k 209.0 20.0 11.0 GB current
Batching Results
Batch Size TG tok/s Speedup
20.5 1.00×
39.5 1.93×
53.9 2.63×