The inference-optimization/Qwen3-1.6B-A0.9B galaxy

2 models are built on inference-optimization/Qwen3-1.6B-A0.9B: 2 quantized, 0 fine-tuned, 0 adapters and 0 merges. Together they were downloaded 16,200 times in the last 30 days.

Most downloaded direct derivatives

• mradermacher/Qwen3-1.6B-A0.9B-i1-GGUF (quantized), 613 downloads in 30 days
• mradermacher/Qwen3-1.6B-A0.9B-GGUF (quantized), 292 downloads in 30 days