← Back to community benchmarks

Qwen3.5-9B

M1 (8c) · 16 GB · 4bit · 2026-04-15
Performance
1k
tokens
71.9
PP tok/s
10.5
TG tok/s
14236
TTFT (ms)
5.7
Peak mem (GB)
Hardware
Chip M1 (8c)
Memory 16 GB
GPU Cores 8
Software
oMLX v0.3.5
macOS macOS 26.4
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 71.9 10.5 5.7 GB current
4k 75.9 10.9 6.3 GB view
8k 76.5 10.7 6.7 GB view
Batching Results
Batch Size TG tok/s Speedup
10.5 1.00×
18.5 1.76×
18.8 1.79×
3.2 0.30×