distilbart-mnli-12-3 is a distilled BART model fine-tuned on MNLI for zero-shot text classification, so it runs on platforms that host Hugging Face models or let you run open models. Hugging Face hosts it directly with a text-classification task interface 2, Replicate offers a cloud API for open-source models including a BART-large-MNLI zero-shot classifier 1, and Ollama can run open models locally 10.
- 1
Hugging Facehuggingface.coverified and signed
Hosts open models like distilbart-mnli-12-3 and offers a text-classification task that includes zero-shot classification for custom labels 2.
official:MCP server · @huggingface/mcp-clientSDK · huggingface-hubCLI · text-embeddings-inferencerepository · pwc-cliskill · hf-cli+23 community tools built for it
for agents: text_classification · image_classification · image-classification
- 2
Replicatereplicate.comverified and signed
Runs open-source machine learning models through a cloud API, including a BART-large-MNLI zero-shot text classifier 1.
+14 community tools built for it
for agents: georgedavila/bart-large-mnli-classifier · shefa/turbo-enigma · microsoft/phi-3-mini-128k-instruct
- 3
Ollamaollama.comwebsite read, tools not yet checked
Runs open AI models locally or in the cloud on macOS, Windows, and Linux, so open models can be used without a hosted API 10.
+141 community tools built for it
Sources
- 1Replicate - Run AI with an APIreplicate.com · read 2026-10-29
- 2Hugging Face – The AI community building the future.huggingface.co · read 2026-10-29
- 10Ollama · Run AI models locally and in the cloudollama.com · read 2026-10-29
For agents: the 10 actions behind this answer
georgedavila/bart-large-mnli-classifier · georgedavila/bart-large-mnli-classifier verified and signed
Zero-shot classifier which classifies text into categories of your choosing. Returns a dictionary of the most likely class and all class likelihoods.
text_classification · Hugging Face (Activepieces) verified and signed
Text Classification — Classify text into categories using Hugging Face models - includes zero-shot classification for custom categories
createClassification · OpenAI API verified and signed
Classifies the specified `query` using provided examples. The endpoint first [searches](/docs/api-reference/searches) over the labeled examples to select the ones most relevant for the particular que
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
tao-finetune-clip · tao-finetune-clip verified and signed
CLIP vision-language model for image-text retrieval, zero-shot classification, embedding extraction, ONNX export, and TensorRT deployment. Use when fine-tuning or training CLIP, running zero-shot classification, computing image embeddings, or deploying CLIP to ONNX/TensorRT. This is a single-action
MXNet · sagemaker verified and signed
predict_node_classification · neo4j-gds found in code, not yet checked
Predict class labels for nodes in a projected graph using a trained node classification model from the model catalog
python · fastcore verified and signed
radar-get-ai-inference-summary-by-model · Cloudflare API verified and signed
Get Workers AI models summary
· Ollama website read, tools not yet checked
Ollama is the easiest way to run and build with open AI models locally or in the cloud on macOS, Windows, and Linux.
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.