Ollama registry preview

Download a model with Ollama.

Use the Hugging Bay hostname in the model name. Ollama checks each downloaded file against its fingerprint (SHA-256).

Get the commands

Download and run

ollama pull huggingbay.xyz/qwen/qwen2.5-0.5b-instruct:q4_k_m
ollama run huggingbay.xyz/qwen/qwen2.5-0.5b-instruct:q4_k_m

Find a supported tag

curl -fsS https://huggingbay.xyz/v2/qwen/qwen2.5-0.5b-instruct/tags/list

Names use lowercase Hugging Face owner and repository names, with the final -GGUF optional. Tags name the quantization, such as q4_k_m. Use an explicit tag.

What is supported

The preview supports Qwen2.5 text chat with a matching extracted chat template. Only public, verified, currently available single-file GGUF models appear. Split files, tool calls and other templates are not supported yet.

Unknown or ambiguous tags return 404. Temporary availability failures return 503. A file hash checks bytes; it does not prove that a model runs on your hardware or grants license permission.

The model runs in your Ollama instance.

Privacy · Licensing