Instructions to use mradermacher/R3-Qwen3-4B-4k-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mradermacher/R3-Qwen3-4B-4k-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("mradermacher/R3-Qwen3-4B-4k-GGUF", dtype="auto")

llama-cpp-python

How to use mradermacher/R3-Qwen3-4B-4k-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="mradermacher/R3-Qwen3-4B-4k-GGUF",
	filename="R3-Qwen3-4B-4k.IQ4_XS.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use mradermacher/R3-Qwen3-4B-4k-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf mradermacher/R3-Qwen3-4B-4k-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf mradermacher/R3-Qwen3-4B-4k-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf mradermacher/R3-Qwen3-4B-4k-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf mradermacher/R3-Qwen3-4B-4k-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/R3-Qwen3-4B-4k-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf mradermacher/R3-Qwen3-4B-4k-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/R3-Qwen3-4B-4k-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf mradermacher/R3-Qwen3-4B-4k-GGUF:Q4_K_M

Use Docker

docker model run hf.co/mradermacher/R3-Qwen3-4B-4k-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use mradermacher/R3-Qwen3-4B-4k-GGUF with Ollama:
```
ollama run hf.co/mradermacher/R3-Qwen3-4B-4k-GGUF:Q4_K_M
```

Unsloth Studio

How to use mradermacher/R3-Qwen3-4B-4k-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/R3-Qwen3-4B-4k-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/R3-Qwen3-4B-4k-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/R3-Qwen3-4B-4k-GGUF to start chatting

How to use mradermacher/R3-Qwen3-4B-4k-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf mradermacher/R3-Qwen3-4B-4k-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/R3-Qwen3-4B-4k-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use mradermacher/R3-Qwen3-4B-4k-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf mradermacher/R3-Qwen3-4B-4k-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/R3-Qwen3-4B-4k-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use mradermacher/R3-Qwen3-4B-4k-GGUF with Docker Model Runner:
```
docker model run hf.co/mradermacher/R3-Qwen3-4B-4k-GGUF:Q4_K_M
```

Lemonade

How to use mradermacher/R3-Qwen3-4B-4k-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull mradermacher/R3-Qwen3-4B-4k-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.R3-Qwen3-4B-4k-GGUF-Q4_K_M

List all available models

lemonade list

mradermacher commited on May 22, 2025

Commit

efe7458

verified ·

1 Parent(s): 983c7c0

uploaded from rain

Browse files

Files changed (13) hide show

.gitattributes +12 -0
R3-Qwen3-4B-4k.IQ4_XS.gguf +3 -0
R3-Qwen3-4B-4k.Q2_K.gguf +3 -0
R3-Qwen3-4B-4k.Q3_K_L.gguf +3 -0
R3-Qwen3-4B-4k.Q3_K_M.gguf +3 -0
R3-Qwen3-4B-4k.Q3_K_S.gguf +3 -0
R3-Qwen3-4B-4k.Q4_K_M.gguf +3 -0
R3-Qwen3-4B-4k.Q4_K_S.gguf +3 -0
R3-Qwen3-4B-4k.Q5_K_M.gguf +3 -0
R3-Qwen3-4B-4k.Q5_K_S.gguf +3 -0
R3-Qwen3-4B-4k.Q6_K.gguf +3 -0
R3-Qwen3-4B-4k.Q8_0.gguf +3 -0
R3-Qwen3-4B-4k.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
+R3-Qwen3-4B-4k.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
+R3-Qwen3-4B-4k.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+R3-Qwen3-4B-4k.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+R3-Qwen3-4B-4k.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+R3-Qwen3-4B-4k.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+R3-Qwen3-4B-4k.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+R3-Qwen3-4B-4k.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+R3-Qwen3-4B-4k.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+R3-Qwen3-4B-4k.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+R3-Qwen3-4B-4k.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+R3-Qwen3-4B-4k.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+R3-Qwen3-4B-4k.f16.gguf filter=lfs diff=lfs merge=lfs -text

+version https://git-lfs.github.com/spec/v1
+oid sha256:776f2293693bbbcbe82530be104588b1c8b428faf07b74554a23176bb0aeea70
+size 2286316864

+version https://git-lfs.github.com/spec/v1
+oid sha256:4a7f3972caa33ef97e31669ce1148735e23bb867c3ce08e0138b352eb79a94bf
+size 1669500224

+version https://git-lfs.github.com/spec/v1
+oid sha256:b5cf7db398a8b2c2561e396212ddc2141141a64750858436f57f264b602de9a9
+size 2239786304

+version https://git-lfs.github.com/spec/v1
+oid sha256:2bac193b437f5363f1a5773827d07e137ed640f732c689c848f92ea601d070b9
+size 2075618624

+version https://git-lfs.github.com/spec/v1
+oid sha256:04b54bcae09a3c5c0ad6c007c769d544bcee67907cd5254ba5b32aacabc0fc4c
+size 1886997824

+version https://git-lfs.github.com/spec/v1
+oid sha256:3feb34b65d304671601d9c91416487cb31421ef876fa69a64e89c7d94383e1fb
+size 2497281344

+version https://git-lfs.github.com/spec/v1
+oid sha256:e47d496a41fdd1c006a37bb02c70cbc1563bf2ac9460b3ec666c545c3210054b
+size 2383310144

+version https://git-lfs.github.com/spec/v1
+oid sha256:24987e2130d5363abc6547ac0a43da9661e7ded74918bf2f97ddff4f95fa4d6b
+size 2889514304

+version https://git-lfs.github.com/spec/v1
+oid sha256:e0c169c244d81d47453f41f5ca3c9520e03c9e4829682c93e0bc530e75c9e3bf
+size 2823712064

+version https://git-lfs.github.com/spec/v1
+oid sha256:a2e1af005d35293ff6fb8bb1f037b2d2407dc828bf053a814886576dff93d1eb
+size 3306261824

	@@ -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 sha256:8ad4ce9c15a68444d9cd7bbdddc2d1a9265fe9c315fb3f3f7ab24fc323126caf
+size 4280405824

+version https://git-lfs.github.com/spec/v1
+oid sha256:e6a48dc6b7f2acda97fbd788367d696ef29b2673e616429b94d670a8a80e72c3
+size 8051285824