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

Libraries

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

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

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

Use Docker

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

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

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

Run Pi

# Start Pi in your project directory:
pi

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

Lemonade

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

Pull the model

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

Run and chat with the model

lemonade run user.Qwen3-4B-Base-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

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

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use mradermacher/Qwen3-4B-Base-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-Base-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-Base-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"

mradermacher commited on Apr 29, 2025

Commit

eb2c2b8

verified ·

1 Parent(s): 572f57f

uploaded from marco

Browse files

Files changed (13) hide show

.gitattributes +12 -0
Qwen3-4B-Base.IQ4_XS.gguf +3 -0
Qwen3-4B-Base.Q2_K.gguf +3 -0
Qwen3-4B-Base.Q3_K_L.gguf +3 -0
Qwen3-4B-Base.Q3_K_M.gguf +3 -0
Qwen3-4B-Base.Q3_K_S.gguf +3 -0
Qwen3-4B-Base.Q4_K_M.gguf +3 -0
Qwen3-4B-Base.Q4_K_S.gguf +3 -0
Qwen3-4B-Base.Q5_K_M.gguf +3 -0
Qwen3-4B-Base.Q5_K_S.gguf +3 -0
Qwen3-4B-Base.Q6_K.gguf +3 -0
Qwen3-4B-Base.Q8_0.gguf +3 -0
Qwen3-4B-Base.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-Base.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-4B-Base.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-4B-Base.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-4B-Base.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-4B-Base.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-4B-Base.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-4B-Base.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-4B-Base.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-4B-Base.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-4B-Base.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-4B-Base.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-4B-Base.f16.gguf filter=lfs diff=lfs merge=lfs -text

+version https://git-lfs.github.com/spec/v1
+oid sha256:44e2ee5d161ab7d7c5f8380121b0a519ba6b61177b3ffb451c8c95feb69b5163
+size 2286316256

+version https://git-lfs.github.com/spec/v1
+oid sha256:59ec04cf198acd5ab34636a960ba8e27cb244c7e777413cf3f9d8d19c477bf92
+size 1669499616

+version https://git-lfs.github.com/spec/v1
+oid sha256:ce0d383326747a31192dc2b816caca17b27e0dbfa5e4a7187a0a30b536e32a7b
+size 2239785696

+version https://git-lfs.github.com/spec/v1
+oid sha256:3699e49319e549848581b07de65b8b14715c37bc8ccc2b834af1ee0df49366f8
+size 2075618016

+version https://git-lfs.github.com/spec/v1
+oid sha256:45b6afe6da580081d672b381d0e15916ffc22005190ccb088e46ae9ccdb5708e
+size 1886997216

+version https://git-lfs.github.com/spec/v1
+oid sha256:a7eb1d92eaf34e116f8b522aeeaf4072e66d69b5b10676e0cb7cd9e11889bed6
+size 2497280736

+version https://git-lfs.github.com/spec/v1
+oid sha256:d1ea886b5217152ad488f7b7585b7b8fe33a69dec89bdf0c27b60327b4558f8a
+size 2383309536

+version https://git-lfs.github.com/spec/v1
+oid sha256:699936b83664f71a4c1d129a1e10b02c1909e8edfdd32962cea75259f4f92093
+size 2889513696

+version https://git-lfs.github.com/spec/v1
+oid sha256:8e0b0117a0b884adeff4f7fede3b39bb1b03e8824ec7aeef309918bb0aae913a
+size 2823711456

+version https://git-lfs.github.com/spec/v1
+oid sha256:bbdab7d0668c0319116413caa0990e5d98a1f64cd6d41bc1ec608eb0d25f55dd
+size 3306261216

	@@ -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 sha256:4498bfc249d7597bef6e4bff1637c4cb9c6434974cada81b68a26974e23be977
+size 4280405216

+version https://git-lfs.github.com/spec/v1
+oid sha256:860a78636750428e98321e859afbef487a5d31f1545ce261d0f74eed412da173
+size 8051285216