You can deploy this model and start earning money today!

pubertcs/
Ornith-1.0-9B-IL2CPP-Decompiler-GGUF

Name: Ornith-1.0-9B-IL2CPP-Decompiler-GGUF
Availability: InStock

Views

No views yet

Ornith-1.0-9B-IL2CPP-Decompiler-GGUF

This repository contains GGUF quantized versions of pubertcs/Ornith-1.0-9B-IL2CPP-Decompiler.

The base model is a distillation of Ornith-1.0-9B trained on 5,000 IL2CPP conversion examples from Deepseek-V4-Flash.

File	Quant Type	Size	Quality
`ornith-il2cpp-Q8_0.gguf`	Q8_0	~9.5 GB	Highest quality, near lossless
`ornith-il2cpp-Q4_K_M.gguf`	Q4_K_M	~5.5 GB	Recommended balance of size and quality
`ornith-il2cpp-Q4_K_S.gguf`	Q4_K_S	~5.1 GB	Slightly smaller, minor quality drop
`ornith-il2cpp-Q3_K_M.gguf`	Q3_K_M	~4.3 GB	Smallest size, noticeable quality drop

./llama-cli -m ornith-il2cpp-Q4_K_M.gguf -p "Convert this C# script to IL2CPP:\n\n" -n 512 --temp 0.6

bash

ollama create ornith-il2cpp -f Modelfile
ollama run ornith-il2cpp

Simply download your preferred .gguf file from the "Files and versions" tab and load it into your local inference UI.