Instructions to use mradermacher/Agentic-Qwen3-4B-e12-lr4-b2-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mradermacher/Agentic-Qwen3-4B-e12-lr4-b2-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("mradermacher/Agentic-Qwen3-4B-e12-lr4-b2-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use mradermacher/Agentic-Qwen3-4B-e12-lr4-b2-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 mradermacher/Agentic-Qwen3-4B-e12-lr4-b2-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf mradermacher/Agentic-Qwen3-4B-e12-lr4-b2-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 mradermacher/Agentic-Qwen3-4B-e12-lr4-b2-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf mradermacher/Agentic-Qwen3-4B-e12-lr4-b2-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 mradermacher/Agentic-Qwen3-4B-e12-lr4-b2-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf mradermacher/Agentic-Qwen3-4B-e12-lr4-b2-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 mradermacher/Agentic-Qwen3-4B-e12-lr4-b2-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf mradermacher/Agentic-Qwen3-4B-e12-lr4-b2-GGUF:Q4_K_M

Use Docker

docker model run hf.co/mradermacher/Agentic-Qwen3-4B-e12-lr4-b2-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use mradermacher/Agentic-Qwen3-4B-e12-lr4-b2-GGUF with Ollama:
```
ollama run hf.co/mradermacher/Agentic-Qwen3-4B-e12-lr4-b2-GGUF:Q4_K_M
```

Unsloth Studio

How to use mradermacher/Agentic-Qwen3-4B-e12-lr4-b2-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for mradermacher/Agentic-Qwen3-4B-e12-lr4-b2-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for mradermacher/Agentic-Qwen3-4B-e12-lr4-b2-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for mradermacher/Agentic-Qwen3-4B-e12-lr4-b2-GGUF to start chatting

How to use mradermacher/Agentic-Qwen3-4B-e12-lr4-b2-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf mradermacher/Agentic-Qwen3-4B-e12-lr4-b2-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "mradermacher/Agentic-Qwen3-4B-e12-lr4-b2-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use mradermacher/Agentic-Qwen3-4B-e12-lr4-b2-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf mradermacher/Agentic-Qwen3-4B-e12-lr4-b2-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 "mradermacher/Agentic-Qwen3-4B-e12-lr4-b2-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"

Docker Model Runner
How to use mradermacher/Agentic-Qwen3-4B-e12-lr4-b2-GGUF with Docker Model Runner:
```
docker model run hf.co/mradermacher/Agentic-Qwen3-4B-e12-lr4-b2-GGUF:Q4_K_M
```

Lemonade

How to use mradermacher/Agentic-Qwen3-4B-e12-lr4-b2-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull mradermacher/Agentic-Qwen3-4B-e12-lr4-b2-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Agentic-Qwen3-4B-e12-lr4-b2-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use mradermacher/Agentic-Qwen3-4B-e12-lr4-b2-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 mradermacher/Agentic-Qwen3-4B-e12-lr4-b2-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 mradermacher/Agentic-Qwen3-4B-e12-lr4-b2-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

@@ -33,3 +33,15 @@ 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
+Agentic-Qwen3-4B-e12-lr4-b2.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
+Agentic-Qwen3-4B-e12-lr4-b2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Agentic-Qwen3-4B-e12-lr4-b2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Agentic-Qwen3-4B-e12-lr4-b2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Agentic-Qwen3-4B-e12-lr4-b2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Agentic-Qwen3-4B-e12-lr4-b2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Agentic-Qwen3-4B-e12-lr4-b2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Agentic-Qwen3-4B-e12-lr4-b2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Agentic-Qwen3-4B-e12-lr4-b2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Agentic-Qwen3-4B-e12-lr4-b2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Agentic-Qwen3-4B-e12-lr4-b2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Agentic-Qwen3-4B-e12-lr4-b2.f16.gguf filter=lfs diff=lfs merge=lfs -text

mradermacher
/

Agentic-Qwen3-4B-e12-lr4-b2-GGUF

uploaded from leia

+version https://git-lfs.github.com/spec/v1
+oid sha256:a427495c38e7158777e407fe3899622defefeefc925fbf32fd6ae69ff01e7aeb
+size 2286316896

+version https://git-lfs.github.com/spec/v1
+oid sha256:0f0c90c2584d62032870ee7cfdeb9856bf0b26dfc0246491f3d3f072de7f1f0e
+size 1669500256

+version https://git-lfs.github.com/spec/v1
+oid sha256:1cc0e9fcd553231b5abbfa18464d998f601b1d3044a14d2ec3f0ec886e758376
+size 2239786336

+version https://git-lfs.github.com/spec/v1
+oid sha256:76751d792384e9fe1a34f99c3580477b2485edf11dcbeddf7bce503d2ac5b062
+size 2075618656

+version https://git-lfs.github.com/spec/v1
+oid sha256:5cbc40119d2b8a6440ab65ebcfebcc2cd15331625a02593352e440787022bcc0
+size 1886997856

+version https://git-lfs.github.com/spec/v1
+oid sha256:6fc1103094c9db6ddbd5386bb166e2af795a3317613a92c0ed9642b81a1dfb29
+size 2497281376

+version https://git-lfs.github.com/spec/v1
+oid sha256:f5c1922d9a5bf005b0f97003043a2f05e51b3528c3419b40547f904cd1ffa160
+size 2383310176

+version https://git-lfs.github.com/spec/v1
+oid sha256:5df2df871ee602891da3dddf7fd338b324b1b3ee1317072f75dfe472272d280b
+size 2889514336

+version https://git-lfs.github.com/spec/v1
+oid sha256:3686e2749fe89308421be35b99142b0fa09a100dda6f0e5204ecf69c64c751ed
+size 2823712096

+version https://git-lfs.github.com/spec/v1
+oid sha256:cb1c5e7ffd71c76f9a24826af8e3397ab31102bb58860f4b826966616357ea8d
+size 3306261856

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

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

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

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:dae9636e81e79523f7159c1e16be0de3469e5244009e1cc3b6e11138619ab6df
+size 4280405856

+version https://git-lfs.github.com/spec/v1
+oid sha256:9dedcf8dffe7270b1be6a925f4a65f8346b663b28fe763eb687c9e8c6342dab6
+size 8051285856