The inference-optimization/Qwen3.8-1.0B-A0.6B galaxy

1 models are built on inference-optimization/Qwen3.8-1.0B-A0.6B: 1 quantized, 0 fine-tuned, 0 adapters and 0 merges. Together they were downloaded 4,616 times in the last 30 days.

Most downloaded direct derivatives

• TEKIBO/Qwen3.8-1.0B-A0.6B-Q4_0-GGUF (quantized), 129 downloads in 30 days

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.