# tensorless

> tensorless runs a model tuned for a GPU, on the engine it was tuned with, in one command: `tensorless run iamMrDuncan/Qwen3.8-27B-PN3-GGUF`. The first card is the NVIDIA Tesla P100 (16 GB, sm_60). A recipe pins the engine image by digest and the model by revision and sha256, with the measured settings and numbers.

## Documentation Sets

- [Abridged documentation](https://tensorless.dev/llms-small.txt): a compact version of the documentation for tensorless, with non-essential content removed
- [Complete documentation](https://tensorless.dev/llms-full.txt): the full documentation for tensorless
- [Tutorials](https://tensorless.dev/_llms-txt/tutorials.txt): learn tensorless by doing
- [How-to guides](https://tensorless.dev/_llms-txt/how-to-guides.txt): the steps for one task each
- [Reference](https://tensorless.dev/_llms-txt/reference.txt): commands, recipes, images, the PN format and receipts, described completely
- [Explanation](https://tensorless.dev/_llms-txt/explanation.txt): how tensorless works, and why

## Notes

- The complete documentation includes all content from the official documentation
- The content is automatically generated from the same source as the official documentation