Results for “model compression”

243 tools in the directory · Updated 2 Nov 2026

“model compression”Runs on Self-hostedShowing 243 tools

CompactifAIby Multiverse ComputingModel compression and access to compressed AI models through managed API or private deployment.Contact sales
W&B Modelsby CoreWeaveTrack, version, compare, and reproduce model experiments at scaleFreemium
0DIN Scannerby MozillaTest AI models and chat interfaces for security weaknessesFree
Thunderboltby MozillaDeploy an AI client with your own models and agent connectionsFree
MLJAR AutoMLby MLJARTrain and compare predictive models for tabular dataFree
Otariby Mozilla.aiControl model routing, budgets and access through one AI gatewayUnknown
any-guardrailby Mozilla.aiCompare and integrate AI guardrail models through one interfaceFree
llamafileby Mozilla.aiRun local language models from portable executable filesFree
encoderfileby Mozilla.aiPackage embedding and classification models as portable executablesFree
LLMWhispererby UnstractPrepare layout-preserved document text for language-model pipelinesFreemium
Nutanix Enterprise AIby NutanixEnterprise AI platform for governing agents, models, and inference across hybrid infrastructureContact sales
Boomi AI Gatewayby BoomiGovernance, observability, and cost control for AI model and MCP trafficContact sales
Open Finetuningby LyzrFine-tunes open models on your documents and routes tasks to them.$35K/yr
NVIDIA Cosmosby NVIDIAOpen world foundation models, datasets and tools for building physical AI.Free
Gemini APIby GoogleDeveloper API for Gemini models, agents, and multimodal generationFreemium
Amazon Novaby AmazonAmazon's family of foundation models plus a free web site for trying themUnknown
PyTorchby PyTorch FoundationOpen source machine learning framework for building and training deep learning modelsFree
Baidu Qianfanby BaiduBaidu's API platform for accessing ERNIE and open-source foundation models and building Agent applications.Pay as you go
TensorFlow.jsby GoogleJavaScript library for running, retraining and building machine learning models in the browser or Node.jsFree
MiroThinkerby MiroMindMiroThinker is a deep-research agent and open-source model family for research and prediction tasks.Freemium
Superlinked Inference Engineby SuperlinkedManaged Superlinked Inference Engine API for embeddings, reranking, extraction and chat with small modelsPay as you go
Overmindby OvermindA platform for tracing AI applications, preparing data, evaluating models, and training and serving specialized models.Freemium
Gradioby Hugging FaceOpen-source Python library for turning functions and models into web appsFree
Simplismartby SimplismartDeploy, serve, and optimize AI models on shared or dedicated infrastructure.Pay as you go