Instructions to use kuririrn/qwen3-4b-structured-output-lora-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use kuririrn/qwen3-4b-structured-output-lora-gguf with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf kuririrn/qwen3-4b-structured-output-lora-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf kuririrn/qwen3-4b-structured-output-lora-gguf:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf kuririrn/qwen3-4b-structured-output-lora-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf kuririrn/qwen3-4b-structured-output-lora-gguf:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf kuririrn/qwen3-4b-structured-output-lora-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf kuririrn/qwen3-4b-structured-output-lora-gguf:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf kuririrn/qwen3-4b-structured-output-lora-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf kuririrn/qwen3-4b-structured-output-lora-gguf:Q4_K_M

Use Docker

docker model run hf.co/kuririrn/qwen3-4b-structured-output-lora-gguf:Q4_K_M

LM Studio
Jan
Ollama
How to use kuririrn/qwen3-4b-structured-output-lora-gguf with Ollama:
```
ollama run hf.co/kuririrn/qwen3-4b-structured-output-lora-gguf:Q4_K_M
```
Unsloth Desktop

How to use kuririrn/qwen3-4b-structured-output-lora-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf kuririrn/qwen3-4b-structured-output-lora-gguf:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "kuririrn/qwen3-4b-structured-output-lora-gguf:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use kuririrn/qwen3-4b-structured-output-lora-gguf with Docker Model Runner:
```
docker model run hf.co/kuririrn/qwen3-4b-structured-output-lora-gguf:Q4_K_M
```

Lemonade

How to use kuririrn/qwen3-4b-structured-output-lora-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull kuririrn/qwen3-4b-structured-output-lora-gguf:Q4_K_M

Run and chat with the model

lemonade run user.qwen3-4b-structured-output-lora-gguf-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use kuririrn/qwen3-4b-structured-output-lora-gguf with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf kuririrn/qwen3-4b-structured-output-lora-gguf:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default kuririrn/qwen3-4b-structured-output-lora-gguf:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use kuririrn/qwen3-4b-structured-output-lora-gguf with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf kuririrn/qwen3-4b-structured-output-lora-gguf:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "kuririrn/qwen3-4b-structured-output-lora-gguf:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

kuririrn commited on Mar 25

Commit

00db444

verified ·

1 Parent(s): a7690da

Upload folder using huggingface_hub

Browse files

Files changed (3) hide show

.gitattributes +1 -0
README.md +44 -0
qwen3-4b-agent-trajectory-lora-sft_dpo_v3-a-Q4_K_M.gguf +3 -0

.gitattributes CHANGED Viewed

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text

 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+qwen3-4b-agent-trajectory-lora-sft_dpo_v3-a-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text

README.md ADDED Viewed

	@@ -0,0 +1,44 @@

+---
+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。

qwen3-4b-agent-trajectory-lora-sft_dpo_v3-a-Q4_K_M.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:cba060031534469723c5e7ac3efbd505018021d5408a3e5f8f6b0771963908b9
+size 2497279616