← Back to community benchmarks

Qwen3.5-9B

M4 (8c) · 16 GB · 4bit · 2026-03-10
Performance
4k
tokens
53.7
PP tok/s
10.1
TG tok/s
76273
TTFT (ms)
6.8
Peak mem (GB)
Hardware
Chip M4 (8c)
Memory 16 GB
GPU Cores 8
Software
oMLX v0.2.6
macOS macOS 26.2
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 56.7 8.4 6.5 GB view
4k 53.7 10.1 6.8 GB current
Batching Results
Batch Size TG tok/s Speedup
8.4 1.00×
15.3 1.82×
18.1 2.15×