Tensorun

Local LLM development

Accelerate local LLM development.

Train, fine-tune, serve and connect language models on your own hardware, from one recipe. No cluster, no lock-in.

Early development Follow Tensorun-AI on GitHub

Recipes

One file says what to train: model, method and data. Run it, resume it, fork it, sweep it. Every run is frozen into a lock you can reproduce.

Fine-tune locally

LoRA, DPO, ORPO and GRPO on pretrained Qwen2, Llama and Mistral models, with a planner that fits the job to your GPU and a memory guard that recovers from out-of-memory.

Serve

One command serves a run, a model folder or a GGUF file behind an OpenAI-style /v1 API and an Ollama-style /api.

Connect

Point your coding agent or editor at your own model with ready-made profiles for pi, Zed and more.

A proper site is on its way

Docs, downloads and benchmarks will live here once Tensorun is ready for you to try.