Instructions to use mradermacher/Magma-R1-4B-AndroidControl-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mradermacher/Magma-R1-4B-AndroidControl-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("mradermacher/Magma-R1-4B-AndroidControl-GGUF", dtype="auto")

llama-cpp-python

How to use mradermacher/Magma-R1-4B-AndroidControl-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="mradermacher/Magma-R1-4B-AndroidControl-GGUF",
	filename="Magma-R1-4B-AndroidControl.IQ4_XS.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use mradermacher/Magma-R1-4B-AndroidControl-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/Magma-R1-4B-AndroidControl-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf mradermacher/Magma-R1-4B-AndroidControl-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/Magma-R1-4B-AndroidControl-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf mradermacher/Magma-R1-4B-AndroidControl-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/Magma-R1-4B-AndroidControl-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf mradermacher/Magma-R1-4B-AndroidControl-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/Magma-R1-4B-AndroidControl-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf mradermacher/Magma-R1-4B-AndroidControl-GGUF:Q4_K_M

Use Docker

docker model run hf.co/mradermacher/Magma-R1-4B-AndroidControl-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use mradermacher/Magma-R1-4B-AndroidControl-GGUF with Ollama:
```
ollama run hf.co/mradermacher/Magma-R1-4B-AndroidControl-GGUF:Q4_K_M
```

Unsloth Studio new

How to use mradermacher/Magma-R1-4B-AndroidControl-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/Magma-R1-4B-AndroidControl-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/Magma-R1-4B-AndroidControl-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/Magma-R1-4B-AndroidControl-GGUF to start chatting

Docker Model Runner
How to use mradermacher/Magma-R1-4B-AndroidControl-GGUF with Docker Model Runner:
```
docker model run hf.co/mradermacher/Magma-R1-4B-AndroidControl-GGUF:Q4_K_M
```

Lemonade

How to use mradermacher/Magma-R1-4B-AndroidControl-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull mradermacher/Magma-R1-4B-AndroidControl-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Magma-R1-4B-AndroidControl-GGUF-Q4_K_M

List all available models

lemonade list

mradermacher commited on Dec 5, 2025

Commit

ba00925

verified ·

1 Parent(s): bf4bb08

uploaded from nico1

Browse files

Files changed (13) hide show

.gitattributes +12 -0
Magma-R1-4B-AndroidControl.IQ4_XS.gguf +3 -0
Magma-R1-4B-AndroidControl.Q2_K.gguf +3 -0
Magma-R1-4B-AndroidControl.Q3_K_L.gguf +3 -0
Magma-R1-4B-AndroidControl.Q3_K_M.gguf +3 -0
Magma-R1-4B-AndroidControl.Q3_K_S.gguf +3 -0
Magma-R1-4B-AndroidControl.Q4_K_M.gguf +3 -0
Magma-R1-4B-AndroidControl.Q4_K_S.gguf +3 -0
Magma-R1-4B-AndroidControl.Q5_K_M.gguf +3 -0
Magma-R1-4B-AndroidControl.Q5_K_S.gguf +3 -0
Magma-R1-4B-AndroidControl.Q6_K.gguf +3 -0
Magma-R1-4B-AndroidControl.Q8_0.gguf +3 -0
Magma-R1-4B-AndroidControl.f16.gguf +3 -0

@@ -35,3 +35,15 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 Magma-R1-4B-AndroidControl.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
 Magma-R1-4B-AndroidControl.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text

 *tfevents* filter=lfs diff=lfs merge=lfs -text
 Magma-R1-4B-AndroidControl.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
 Magma-R1-4B-AndroidControl.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text
+Magma-R1-4B-AndroidControl.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
+Magma-R1-4B-AndroidControl.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Magma-R1-4B-AndroidControl.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Magma-R1-4B-AndroidControl.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Magma-R1-4B-AndroidControl.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Magma-R1-4B-AndroidControl.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Magma-R1-4B-AndroidControl.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Magma-R1-4B-AndroidControl.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Magma-R1-4B-AndroidControl.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Magma-R1-4B-AndroidControl.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Magma-R1-4B-AndroidControl.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Magma-R1-4B-AndroidControl.f16.gguf filter=lfs diff=lfs merge=lfs -text

+version https://git-lfs.github.com/spec/v1
+oid sha256:1506ecd6b03dde3ec54f62a77130e67f1e5baf99e709905ebe55b0fb58de5559
+size 1753183776

+version https://git-lfs.github.com/spec/v1
+oid sha256:0a3d0c34509c436b2a403f89e3a57c66f321cfbbb3a7cc08155ba2f8e2cb9d70
+size 1274754592

+version https://git-lfs.github.com/spec/v1
+oid sha256:37b0a9cb0631092f0ac9f7b4d286018f402db826f6f11e7ac9c39ae706b4e209
+size 1707390496

+version https://git-lfs.github.com/spec/v1
+oid sha256:baee015a5a3e6cabb084c9db45988d821aa39af20b24216ca9b7896871b2a799
+size 1590474272

+version https://git-lfs.github.com/spec/v1
+oid sha256:9d771a81e828f4cb6d976fd1788691fe4560cb64da156e2cbc5b49fbef4b3208
+size 1454356000

+version https://git-lfs.github.com/spec/v1
+oid sha256:61cd575e9ea9d4030f60efa897aba9d5ce0467b8ac849015b97238b0dee2a7b7
+size 1929901600

+version https://git-lfs.github.com/spec/v1
+oid sha256:42f0233f06032c41d452eec8b2fc812dedafbc1c1d8a3a5d8a5fc696271b5fca
+size 1834382880

+version https://git-lfs.github.com/spec/v1
+oid sha256:baace290622a676855367065dcc49d90c9644ac59cc49f7abde240a84db538f3
+size 2224813600

+version https://git-lfs.github.com/spec/v1
+oid sha256:ce9f254dc2bfa9c5bd127d2538078f4b026f320534ed28411daaabb0578b4d6d
+size 2169665056

+version https://git-lfs.github.com/spec/v1
+oid sha256:3df19a4ed70456ba5388b1a6c541e7ebbe22b373074d32d89e3dc345dcf65e09
+size 2538157600

	@@ -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 sha256:754186443a347ea1157010fb1d038d490716c1f27cdc1b2c024d00b512b26faa
+size 3285474848

+version https://git-lfs.github.com/spec/v1
+oid sha256:dc80cd367003a087894ba4ce3d7383e44cf1c4bdbd5ce805fdb381b7c026a0e8
+size 6178315808