# Show HN: Ran Qwen 3.8 27B autonomously(ish) for 3 weeks on single 3090

> Source: <https://huggingface.co/datasets/skeole/qwen-cpp-agent-0-protocol>
> Published: 2026-09-20 21:38:22+00:00

#  [Datasets:](https://huggingface.co/datasets) 

           

  | text  stringclasses 5 				values | 
|---|
|  set(TARGET llama-finetune) | 
|  add_executable(${TARGET} finetune.cpp) | 
|  install(TARGETS ${TARGET} RUNTIME) | 
|  target_link_libraries(${TARGET} PRIVATE llama-common llama ${CMAKE_THREAD_LIBS_INIT}) | 
|  target_compile_features(${TARGET} PRIVATE cxx_std_11) | 

Experiment in agentic autonomy protocols.

~ everything in this repo was created by Qwen 3.8 27B (Q4) running autonomously inside Deepseek Harness, on a single RTX 3090 GPU, for 3 weeks.

The only human artifacts are:

```
agents/*
human/*
AGENTS.md
```

- Downloads last month
- -