From GitHub
- GitHub stars
- 23
- Last code update
- 2026-08-04
nano-llm-posttraining
Minimal LLM post-training experiments supporting SFT, DPO, and GRPO on an 8GB GPU.
Why it made the shelf
This is an open-source developer tool and library for running LLM post-training on consumer hardware.
On 2 boards
- First seen
- 2 months ago
- Best score
- 21 points
Official signals
What the source shows.
Sourced facts from the places where this tool ships.
Behind the tool
Who built it. How it grew.
People, backing, growth, and ownership. Every claim links to its source.
Official sitegithub.com
Source review current
Public trail
Where it showed up
1 reference from 1 publisher.
- First trace
- Hacker News2 months ago
- 01Hacker NewsFirst trace
Minimal LLM Post-Training Experiments on an 8GB GPU (SFT, DPO, GRPO)