Discover Models

Open-weight models in GGUF format, searchable by name or repository. Results come from the Hugging Face Hub — opening one takes you there to download it.

Loading models…

Before you download

A model that does not fit in memory will load slowly or not at all, and the failure looks like a broken runtime rather than a size problem. Check the size against your machine first — Local AI covers hardware fit, and System requirements covers the runtime itself.

Running a model you found here

BCCLI does not download models. Import the file with the runtime you use — Ollama, LM Studio, or any OpenAI-compatible server — then check that BCCLI can see it:

bccli models
bccli -m provider/model

Legacy command reference

warning

Legacy managed-runtime reference. The commands below belong to the older desktop/managed llama.cpp preview and are legacy, not the current BCCLI v0.4 command surface. Use BCCLI and Local AI for current instructions.

botconnector models search qwen
botconnector get Qwen/Qwen2.5-Coder-7B-Instruct-GGUF@Q4_K_M
botconnector run Qwen/Qwen2.5-Coder-7B-Instruct-GGUF