← Back to community benchmarks

Qwen3.5-9B

M4 Pro (16c) · 24 GB · 4bit · 2026-03-09
Performance
1k
tokens
349.7
PP tok/s
46.6
TG tok/s
2928
TTFT (ms)
6.7
Peak mem (GB)
Hardware
Chip M4 Pro (16c)
Memory 24 GB
GPU Cores 16
Software
oMLX v0.2.6
macOS macOS 26.3
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 349.7 46.6 6.7 GB current
4k 355.3 45.9 7.0 GB view
Batching Results
Batch Size TG tok/s Speedup
46.6 1.00×
78.4 1.68×
82.9 1.78×