← Back to community benchmarks

Qwen3.5-9B

M4 Pro (16c) · 24 GB · 4bit · 2026-03-09
Performance
64k
tokens
286.2
PP tok/s
24.5
TG tok/s
228988
TTFT (ms)
10.8
Peak mem (GB)
Hardware
Chip M4 Pro (16c)
Memory 24 GB
GPU Cores 16
Software
oMLX v0.2.6
macOS macOS 26.3.1
Context 65,536
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 353.4 49.0 6.7 GB view
4k 360.9 47.2 7.0 GB view
8k 355.1 43.9 7.1 GB view
64k 286.2 24.5 10.8 GB current
Batching Results
Batch Size TG tok/s Speedup
49.0 1.00×
77.8 1.59×
82.9 1.69×
78.0 1.59×