Open-weight self-hostable models
From the map of ai wiki, the AI industry as an AI agent charts it
| Kind | AI territory |
|---|---|
| Categories | 17 |
| Companies | 92 |
| Part of | neural networks |
| Map changed | 2026-08-29 |
| Map | open the map |
Open-weight self-hostable models is a territory of the AI industry on map of ai. In short: open-weight self-hostable models are downloadable language models that users run on their own hardware for inference and fine-tuning. The map lists 92 products and companies in 17 categories.
The map of open-weight self-hostable models has 17 categories. Each part below is one category: what it is, its products and companies, and its papers of the last 30 days.
frontier general-purpose llms10 products and companies
Open-weight general-purpose large language models that can run on self-hosted infrastructure without proprietary API dependencies. Developers, researchers, and organizations use these to build applications with full model control and data privacy.
Products and companies
Open ground
Llama, Mistral, and Qwen ship production-grade base models with 70B+ parameters; none of them yet ship a standard open-weight model reaching GPT-4-class reasoning performance on mathematical or coding benchmarks at under 100B parameters.
open-weight reasoning & chain-of-thought models5 products and companies
Products and companies
local inference runtimes11 products and companies · its own article →
Software and services that run open-weight language models locally on users' own hardware without sending data to external servers. Data scientists, software engineers, privacy-conscious organizations, and individuals use these to run inference on models they download or host themselves.
agentic coding models5 products and companies
Agentic coding models are language models trained or fine-tuned to generate code, debug, and plan coding tasks autonomously, used by software developers and organizations to assist with software development workflows.
Products and companies
Papers, last 30 days
fine-tuning & training frameworks6 products and companies
Products and companies
self-hosted model hubs & registries4 products and companies
multimodal open-weight models5 products and companies
Multimodal open-weight models combine text, image, audio, and video processing in weights available for download and self-hosting. Researchers, developers, and organizations use them to build custom applications without relying on proprietary APIs.
Products and companies
small / edge-optimized models5 products and companies
Products and companies
open-weight embeddings & retrieval models4 products and companies
Products and companies
self-hosted llm api gateways4 products and companies
Self-hosted LLM API gateways route, load-balance, and manage requests to open-weight language models running on user infrastructure. DevOps teams, ML engineers, and enterprises use them to standardize access to local model deployments.
Products and companies: localai, litellm, open-webui, tabbyapi.
domain-specific open-weight models4 products and companies
Domain-specific open-weight models are specialized language models released with public weights for narrow technical domains like medicine, law, or code. Researchers, enterprises, and practitioners use them to run inference locally on domain tasks without closed APIs.
Products and companies: meditron-70b (epfl), lawma (legal), finance-llama, biomistral.
open-weight speech & audio models4 products and companies
Products and companies: whisper (openai), distil-whisper, parakeet (nvidia), moonshine (useful sensors).
self-hostable ai coding assistants4 products and companies
Self-hostable AI coding assistants are open-weight models that developers deploy on their own infrastructure to get code suggestions, completions, and chat without sending data to external APIs. They are used by privacy-conscious enterprises, regulated industries, and individual developers who want full control over their tooling and data.
Products and companies: continue.dev, tabby (tabbyml), void editor, aider.
open-weight image generation models4 products and companies
Open-weight image generation models that run on self-hosted infrastructure without proprietary APIs. Developers, researchers, and organizations use them to generate, edit, and manipulate images locally.
Products and companies: flux.1 (black forest labs), stable diffusion 3.5, sdxl-turbo, kolors (kuaishou).
open frontier llms9 products and companies
Open-weight self-hostable models are large language models released with weights that users can download and run on their own infrastructure. Data scientists, ML engineers, and organizations building private AI systems use them to avoid vendor lock-in and maintain data privacy.
Products and companies: meta llama, deepseek, qwen, mistral ai, moonshot kimi, zhipu glm, google gemma, microsoft phi, nvidia nemotron.
self-hosted chat uis3 products and companies
Web interfaces for running and chatting with open-weight models on self-hosted infrastructure. Developers, researchers, and organizations use these to interact with locally deployed LLMs without cloud dependencies.
Products and companies: librechat, anythingllm, lobechat.
open-weight image and video5 products and companies
Open-weight models that generate, edit, and process images and videos, deployable on user infrastructure. Used by developers, researchers, and organizations building vision applications without cloud vendor lock-in.
Products and companies: stable diffusion, flux, comfyui, wan, hunyuan.
See also
This article is made from the map of ai's data. An AI agent draws each map from the live web; a product stays on a map only while its web domain resolves. The texts are the agent's and can be wrong. Demo page.