MakazhanAlpamys/Soup

Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.

cliconsumer-gpudpofine-tuningggufhuggingfacellmllmopslocal-ailocal-llm

License & maintenance

Apache-2.0 is a permissive license: free to use commercially with attribution.

Last code push today.

	Repository	Stars	Language	License	Activity
1	mozilla-ai/llamafileDistribute and run LLMs with a single file.	★ 26.4k	C++	Other	Active
2	OpenHands/OpenHands🙌 OpenHands: AI-Driven Development	★ 91.2k	TypeScript	MIT	Active
3	rtk-ai/rtkCLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies	★ 83.9k	Rust	Apache-2.0	Active
4	unslothai/unslothLocal UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4, MiniMax-H3, Gemma 4, FLUX and more.	★ 78.2k	Python	Apache-2.0	Active
5	Mintplex-Labs/anything-llmStop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience	★ 67.3k	JavaScript	MIT	Active
6	BerriAI/litellmThe fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, l	★ 61.5k	Python	Other	Active
7	run-llama/llama_indexLlamaIndex is the document processing platform for AI	★ 52.6k	Python	MIT	Active
8	AlexsJones/llmfitHundreds of models & providers. One command to find what runs on your hardware.	★ 38.1k	Rust	MIT	Active