pi05-libero-gguf is a specific model name, not a product in this list, so the best fit is a model hub where GGUF model files are published and run locally. Hugging Face hosts the model hub and offers an SDK and MCP server for finding and loading models 1, and its local-model action covers finding GGUFs and running them with llama.cpp 1. Replicate runs open-source models through a cloud API 2, and OpenAI lists the models available to an account 8.
A question back: Do you want to run pi05-libero-gguf locally on your own hardware, or call it through a hosted cloud API?
- 1
Hugging Facehuggingface.coverified and signed
Hosts public models and datasets and provides an SDK (huggingface-hub) and an MCP server for accessing them, with an action for finding GGUF files and running them locally with llama.cpp 1.
official:MCP server · @huggingface/mcp-clientSDK · huggingface-hubCLI · text-embeddings-inferencerepository · pwc-cliskill · hf-cli+23 community tools built for it
for agents: huggingface-local-models · models · model-hub
- 2
Replicatereplicate.comverified and signed
Runs open-source machine learning models through a cloud API, callable from code with a single run call 2.
+14 community tools built for it
for agents: kcaverly/openchat-3.5-1210-gguf · openai/gpt-5-nano · matt-bornstein/nspm1
- 3
OpenAI APIopenai.comfound in code, not yet checked
Lists and retrieves the models available to an OpenAI account through its API 8.
official:MCP server · mcp-extensionsAPI · OpenAI APISDK · openailibrary · OpenAICLI · openai-whisper+177 community tools built for it
for agents: python · list_models · retrieveModel
Sources
- 1Hugging Face – The AI community building the future.huggingface.co · read 2026-10-29
- 2Replicate - Run AI with an APIreplicate.com · read 2026-10-29
- 8babysit-pr — openai/codexskills.sh · read 2026-10-29
Left out: git-flow-next, because each one's own page says it is retired or discontinued.
For agents: the 10 actions behind this answer
huggingface-local-models · huggingface-local-models verified and signed
Use to select models to run locally with llama.cpp and GGUF on CPU, Mac Metal, CUDA, or ROCm. Covers finding GGUFs, quant selection, running servers, exact GGUF file lookup, conversion, and OpenAI-compatible local serving.
kcaverly/openchat-3.5-1210-gguf · kcaverly/openchat-3.5-1210-gguf verified and signed
The "Overall Best Performing Open Source 7B Model" for Coding + Generalization or Mathematical Reasoning
model-recommendation · model-recommendation verified and signed
Analyze chatmode or prompt files and recommend optimal AI models based on task complexity, required capabilities, and cost-efficiency
get_semantic_model · fabric-toolbox found in code, not yet checked
Get details of a specific semantic model by its GUID within a workspace.
llm · GLM-5 verified and signed
Task: LLM
train_link_prediction_model · neo4j-gds found in code, not yet checked
Train a link prediction model on a projected graph and store it in the GDS model catalog under modelName.
load_model · gravitino found in code, not yet checked
Load detailed information of a specific model.
python · gpt-oss found in code, not yet checked
Tensorflow · sagemaker verified and signed
workers-ai-search-model · Cloudflare API verified and signed
Model Search
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.