← Back to community benchmarks

Qwen3.5-9B

M4 Pro (16c) · 24 GB · 4bit · 2026-03-16
Performance
8k
tokens
353.8
PP tok/s
44.4
TG tok/s
23156
TTFT (ms)
7.1
Peak mem (GB)
Hardware
Chip M4 Pro (16c)
Memory 24 GB
GPU Cores 16
Software
oMLX v0.2.11
macOS macOS 15.7.4
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 334.7 46.6 6.7 GB view
4k 349.6 47.1 7.0 GB view
8k 353.8 44.4 7.1 GB current
16k 340.8 39.7 7.6 GB view
32k 320.5 33.1 8.7 GB view
64k 283.3 24.5 10.8 GB view
Batching Results
Batch Size TG tok/s Speedup
46.6 1.00×
77.1 1.65×
83.9 1.80×