#1
Ollama is a local LLM runtime that lets you pull, run, and customize models, offering a CLI and REST API for chat, generation, and embeddings.
179.5k stars17.6k forksMITlast commit Actively maintained
3 self-hosted Fireworks AI alternatives
Cloud inference platform for hosting and serving large language and multimodal models via APIs. Provides managed model hosting, serverless inference endpoints, autoscaling, low-latency and cost-focused performance tooling for production deployment and monitoring.
Alternatives to Fireworks AI
#2
Run LLMs, image, and audio models locally with an OpenAI-compatible API, optional GPU acceleration, and a built-in web UI for managing and testing models.
48.7k stars4.4k forksMITlast commit Actively maintained
#3
Open-source Python framework to build, scale, and deploy multimodal AI services and pipelines with gRPC/HTTP/WebSocket support and Kubernetes/Docker integration.
21.9k stars2.2k forksApache-2.0last commit Slowing down
What replacing Fireworks AI actually involves
Every option on this page is open source and free to run on your own hardware, so you own the data and there is no subscription to cancel. 2 of 3 shipped a commit in the last six months. Licences in this list: MIT, Apache-2.0. In exchange you take on hosting, backups and updates yourself.
Browse everything in GenAI & LLM Platforms.
