---
library_name: gguf
tags:
- gguf
- llama-cpp
- quantized
- local-llm
---

# qwen3-4b-agent-trajectory-lora-sft_dpo_v3-a (GGUF)

## Overview

Hugging Face上またはローカルのモデル/GGUFを元に、GGUF形式へ変換または再量子化し、README付きで再公開したモデルです。

This repository contains a GGUF model prepared for local inference workflows such as LM Studio and llama.cpp.

## Source

- Source type: Hugging Face Transformers model
- Source repo: `kuririrn/qwen3-4b-agent-trajectory-lora-sft_dpo_v3-a`

## Quantization

- Final quantization: `Q4_K_M`
- Final file: `qwen3-4b-agent-trajectory-lora-sft_dpo_v3-a-Q4_K_M.gguf`

## Notes

- This repository is intended for **distribution and local inference**, not for training.
- LM Studio is a **consumer of GGUF**, not a conversion tool itself.
- If the source was a Transformers model, conversion was performed via `llama.cpp`.
- If the source was already a GGUF, it was reused and/or requantized.

## Usage

- Download the `.gguf` file from this repository.
- Import it into LM Studio or use it with llama.cpp-compatible tools.

## Additional Notes

- Base model note: not specified
- License note: please follow the original upstream license and usage terms
- Intended use: LM Studio や llama.cpp 系ツールでのローカル推論、および配布・共有を想定しています。