← Back to community benchmarks

Qwen3.5-9B

M4 (10c) · 24 GB · 4bit · 2026-05-12
Performance
1k
tokens
80.1
PP tok/s
9.1
TG tok/s
12783
TTFT (ms)
5.7
Peak mem (GB)
Hardware
Chip M4 (10c)
Memory 24 GB
GPU Cores 10
Software
oMLX v0.3.9.dev1
macOS macOS 15.7.4
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 80.1 9.1 5.7 GB current
4k 78.3 7.7 6.3 GB view
Batching Results
Batch Size TG tok/s Speedup
9.1 1.00×
13.5 1.48×
14.4 1.58×