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

Libraries

How to use mradermacher/Qwen3-4B-GKD-Tulu-GGUF with Transformers:

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

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

Use Docker

docker model run hf.co/mradermacher/Qwen3-4B-GKD-Tulu-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use mradermacher/Qwen3-4B-GKD-Tulu-GGUF with Ollama:
```
ollama run hf.co/mradermacher/Qwen3-4B-GKD-Tulu-GGUF:Q4_K_M
```

Unsloth Studio

How to use mradermacher/Qwen3-4B-GKD-Tulu-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/Qwen3-4B-GKD-Tulu-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/Qwen3-4B-GKD-Tulu-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/Qwen3-4B-GKD-Tulu-GGUF to start chatting

How to use mradermacher/Qwen3-4B-GKD-Tulu-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/Qwen3-4B-GKD-Tulu-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/Qwen3-4B-GKD-Tulu-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use mradermacher/Qwen3-4B-GKD-Tulu-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/Qwen3-4B-GKD-Tulu-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/Qwen3-4B-GKD-Tulu-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/Qwen3-4B-GKD-Tulu-GGUF with Docker Model Runner:
```
docker model run hf.co/mradermacher/Qwen3-4B-GKD-Tulu-GGUF:Q4_K_M
```

Lemonade

How to use mradermacher/Qwen3-4B-GKD-Tulu-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull mradermacher/Qwen3-4B-GKD-Tulu-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3-4B-GKD-Tulu-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use mradermacher/Qwen3-4B-GKD-Tulu-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/Qwen3-4B-GKD-Tulu-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/Qwen3-4B-GKD-Tulu-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

mradermacher commited on Oct 30, 2025

Commit

8b11c61

verified ·

1 Parent(s): 7b27919

uploaded from leia

Browse files

Files changed (13) hide show

.gitattributes +12 -0
Qwen3-4B-GKD-Tulu.IQ4_XS.gguf +3 -0
Qwen3-4B-GKD-Tulu.Q2_K.gguf +3 -0
Qwen3-4B-GKD-Tulu.Q3_K_L.gguf +3 -0
Qwen3-4B-GKD-Tulu.Q3_K_M.gguf +3 -0
Qwen3-4B-GKD-Tulu.Q3_K_S.gguf +3 -0
Qwen3-4B-GKD-Tulu.Q4_K_M.gguf +3 -0
Qwen3-4B-GKD-Tulu.Q4_K_S.gguf +3 -0
Qwen3-4B-GKD-Tulu.Q5_K_M.gguf +3 -0
Qwen3-4B-GKD-Tulu.Q5_K_S.gguf +3 -0
Qwen3-4B-GKD-Tulu.Q6_K.gguf +3 -0
Qwen3-4B-GKD-Tulu.Q8_0.gguf +3 -0
Qwen3-4B-GKD-Tulu.f16.gguf +3 -0

@@ -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
+Qwen3-4B-GKD-Tulu.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-4B-GKD-Tulu.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-4B-GKD-Tulu.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-4B-GKD-Tulu.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-4B-GKD-Tulu.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-4B-GKD-Tulu.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-4B-GKD-Tulu.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-4B-GKD-Tulu.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-4B-GKD-Tulu.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-4B-GKD-Tulu.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-4B-GKD-Tulu.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-4B-GKD-Tulu.f16.gguf filter=lfs diff=lfs merge=lfs -text

+version https://git-lfs.github.com/spec/v1
+oid sha256:4fbdd671fe37ff963a2c99ef165e71d21415679fc56605f0704c4bdd1d50162d
+size 2286316608

+version https://git-lfs.github.com/spec/v1
+oid sha256:cc2cd74d33f34613ad9e70ef53d52a54fd455e5d6173b925d26b9131538c4cca
+size 1669499968

+version https://git-lfs.github.com/spec/v1
+oid sha256:64731e81c32fed3d40a904231c990a518cf8de829333cdbd104416a49feee0e8
+size 2239786048

+version https://git-lfs.github.com/spec/v1
+oid sha256:ed009b0cab6bfb988b262e14314888886d5c2be08bfa3236cfdf5179cf1e7e36
+size 2075618368

+version https://git-lfs.github.com/spec/v1
+oid sha256:bc0b95e2629c1c46bf1a3ba555c3be1f56c174d01e7df37b068c10ae1ddf46cc
+size 1886997568

+version https://git-lfs.github.com/spec/v1
+oid sha256:a850ae5166e8af8870f2d32c411bbd73c1227f0e114f2d1e8d97ea82b1c4b2c8
+size 2497281088

+version https://git-lfs.github.com/spec/v1
+oid sha256:80ae7d2cef08b6ac61af8a223e79596b974e0ce624f6911988d124767486198b
+size 2383309888

+version https://git-lfs.github.com/spec/v1
+oid sha256:12f0ee83ac39d03aae425aafa810a30ea5ec7916ce9531915abac89e14eb671e
+size 2889514048

+version https://git-lfs.github.com/spec/v1
+oid sha256:0301851e0f40cc1894bfa3d8f0da0e9ccae9f1076ef9065004c59929357b184e
+size 2823711808

+version https://git-lfs.github.com/spec/v1
+oid sha256:0f4238a8b89e16412806587ba45b7ddae9bf96167570d435a37e387337fc669e
+size 3306261568

	@@ -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 sha256:0754fbd15dd5c56a28152f6f73774e8ba4f91646c53523504061eea2d5ddcc7c
+size 4280405568

+version https://git-lfs.github.com/spec/v1
+oid sha256:6ed311fee7495c557a77cefbe004600511c06bad7cdab9cc961d6aa2c339965b
+size 8051285568