hgnetv2_b4.ssld_stage1_in22k_in1k is a timm-style image classification model identifier (HGNetV2-B4 pretrained on ImageNet-22k and fine-tuned on ImageNet-1k), so it is run through a model hub or library that serves timm/Hugging Face weights. Hugging Face hosts pre-trained image classification models with official hub, SDK and CLI access 4, and Replicate runs open-source ML models behind a cloud API 9.
- 1
Hugging Facehuggingface.coverified and signed
Hosts pre-trained image classification models and offers the huggingface-hub SDK and CLI to download and run them 4.
official:MCP server · @huggingface/mcp-clientSDK · huggingface-hubCLI · text-embeddings-inferencerepository · pwc-cliskill · hf-cli+23 community tools built for it
for agents: image_classification · pretrained-models · hf-mem
- 2
Replicatereplicate.comverified and signed
Runs open-source machine learning models through a cloud API, including vision models, if you prefer hosted inference 9.
+14 community tools built for it
for agents: lucataco/paligemma-3b-pt-224 · lucataco/ssd-1b-img2img · lightweight-ai/model1
- 3
NVIDIA TAOnvidia.comverified and signed
PyTorch-based TAO image classification supporting a range of backbones for training and fine-tuning classifiers 3.
official:MCP server · NVIDIA CUDA Docs+84 community tools built for it
for agents: tao-train-image-classification · computer-vision · mistralai
Sources
- 3Brev.dev Consolebrev.nvidia.com · read 2026-10-29
- 4Hugging Face – The AI community building the future.huggingface.co · read 2026-10-29
- 9Replicate - Run AI with an APIreplicate.com · read 2026-10-29
For agents: the 10 actions behind this answer
nano-banana-pro-openrouter · nano-banana-pro-openrouter verified and signed
Generate or edit images via OpenRouter with the Gemini 3 Pro Image model. Use for prompt-only image generation, image edits, and multi-image compositing; supports 1K/2K/4K output.
agent-platform-deploy · agent-platform-deploy verified and signed
Deploy open models or custom weights from Model Garden to Agent Platform endpoints, check the status of an in-progress deployment operation, or clean up resources by undeploying models and deleting endpoints. Use when asked to actively deploy a model, list the Model Garden CATALOG of available model
tao-train-image-classification · tao-train-image-classification verified and signed
PyTorch-based TAO image classification. Supports a wide range of backbones (FAN, EfficientNet, ResNet, etc.) with distillation and quantization for deployment. Use when training, evaluating, distilling, quantizing, exporting, or running inference for a TAO image-classification (PyT) model. Trigger p
image_classification · Hugging Face (Activepieces) verified and signed
Image Classification — Classify images with pre-trained models or custom categories - perfect for content moderation, automated tagging, and smart asset management
retrieveModel · OpenAI API verified and signed
Retrieves a model instance, providing basic information about the model such as the owner and permissioning.
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
workers-ai-post-run-model · Cloudflare API verified and signed
Run a Workers AI model
python · fastcore verified and signed
lucataco/paligemma-3b-pt-224 · lucataco/paligemma-3b-pt-224 verified and signed
PaliGemma 3B, an open VLM by Google, pre-trained with 224*224 input images and 128 token input/output text sequences
· 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.