Instructions to use mradermacher/VisualThinker-R1-Zero-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mradermacher/VisualThinker-R1-Zero-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("mradermacher/VisualThinker-R1-Zero-GGUF", dtype="auto")

llama-cpp-python

How to use mradermacher/VisualThinker-R1-Zero-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="mradermacher/VisualThinker-R1-Zero-GGUF",
	filename="VisualThinker-R1-Zero.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/VisualThinker-R1-Zero-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/VisualThinker-R1-Zero-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf mradermacher/VisualThinker-R1-Zero-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/VisualThinker-R1-Zero-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf mradermacher/VisualThinker-R1-Zero-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/VisualThinker-R1-Zero-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf mradermacher/VisualThinker-R1-Zero-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/VisualThinker-R1-Zero-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf mradermacher/VisualThinker-R1-Zero-GGUF:Q4_K_M

Use Docker

docker model run hf.co/mradermacher/VisualThinker-R1-Zero-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use mradermacher/VisualThinker-R1-Zero-GGUF with Ollama:
```
ollama run hf.co/mradermacher/VisualThinker-R1-Zero-GGUF:Q4_K_M
```

Unsloth Studio new

How to use mradermacher/VisualThinker-R1-Zero-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/VisualThinker-R1-Zero-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/VisualThinker-R1-Zero-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/VisualThinker-R1-Zero-GGUF to start chatting

Docker Model Runner
How to use mradermacher/VisualThinker-R1-Zero-GGUF with Docker Model Runner:
```
docker model run hf.co/mradermacher/VisualThinker-R1-Zero-GGUF:Q4_K_M
```

Lemonade

How to use mradermacher/VisualThinker-R1-Zero-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull mradermacher/VisualThinker-R1-Zero-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.VisualThinker-R1-Zero-GGUF-Q4_K_M

List all available models

lemonade list

mradermacher commited on Mar 19, 2025

Commit

8c0a2a4

verified ·

1 Parent(s): b254a01

uploaded from nico1

Browse files

Files changed (13) hide show

.gitattributes +12 -0
VisualThinker-R1-Zero.IQ4_XS.gguf +3 -0
VisualThinker-R1-Zero.Q2_K.gguf +3 -0
VisualThinker-R1-Zero.Q3_K_L.gguf +3 -0
VisualThinker-R1-Zero.Q3_K_M.gguf +3 -0
VisualThinker-R1-Zero.Q3_K_S.gguf +3 -0
VisualThinker-R1-Zero.Q4_K_M.gguf +3 -0
VisualThinker-R1-Zero.Q4_K_S.gguf +3 -0
VisualThinker-R1-Zero.Q5_K_M.gguf +3 -0
VisualThinker-R1-Zero.Q5_K_S.gguf +3 -0
VisualThinker-R1-Zero.Q6_K.gguf +3 -0
VisualThinker-R1-Zero.Q8_0.gguf +3 -0
VisualThinker-R1-Zero.f16.gguf +3 -0

@@ -34,3 +34,15 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 VisualThinker-R1-Zero.mmproj-fp16.gguf filter=lfs diff=lfs merge=lfs -text

 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 VisualThinker-R1-Zero.mmproj-fp16.gguf filter=lfs diff=lfs merge=lfs -text
+VisualThinker-R1-Zero.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
+VisualThinker-R1-Zero.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+VisualThinker-R1-Zero.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+VisualThinker-R1-Zero.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+VisualThinker-R1-Zero.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+VisualThinker-R1-Zero.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+VisualThinker-R1-Zero.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+VisualThinker-R1-Zero.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+VisualThinker-R1-Zero.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+VisualThinker-R1-Zero.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+VisualThinker-R1-Zero.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+VisualThinker-R1-Zero.f16.gguf filter=lfs diff=lfs merge=lfs -text

+version https://git-lfs.github.com/spec/v1
+oid sha256:fb6d29a3ae17455b6ac9afc98881886784601363dad05c4416fe0b5e72a71722
+size 902181408

+version https://git-lfs.github.com/spec/v1
+oid sha256:16722573d5c2d29fe85331a0a932d3738bafb4240bdd6f932734e68f80ff9db7
+size 676303392

+version https://git-lfs.github.com/spec/v1
+oid sha256:bbed84c9897585ce975cd1c292628cc5eadcc03497e1c7687230a9a86cc7e455
+size 880161312

+version https://git-lfs.github.com/spec/v1
+oid sha256:ce1760e08c1f52788523c6e19eab1fb919afde26cb0dedc40c36ba8d1e67b284
+size 824177184

+version https://git-lfs.github.com/spec/v1
+oid sha256:27bea24c9ed38363ee3f1795404c72a4f637a5a6bcd57dc5d40515503a96919f
+size 760943136

+version https://git-lfs.github.com/spec/v1
+oid sha256:d9ed19196284357a2909f3307cb29fbefac56b2b6bf8be6c7a717298f764bc3a
+size 986047008

+version https://git-lfs.github.com/spec/v1
+oid sha256:a53df937dbecad4f039eee6b0e40811eefe6c0e723d887b980831cc7a9f56288
+size 940311072

+version https://git-lfs.github.com/spec/v1
+oid sha256:7a4e213a23835538cb4351cf9f78896d7599fc01721afeeaeac3197cecf30628
+size 1125048864

+version https://git-lfs.github.com/spec/v1
+oid sha256:f2fed6ce567ec757fbd33e7b9f67e709df6c878e39171d75afcbfcb9c0e0efd1
+size 1098727968

+version https://git-lfs.github.com/spec/v1
+oid sha256:ef27abd3f10b2f11a09070c8f4aa5a7a88c4bab5bf4109aeaaf9fae143a58dc0
+size 1272738336

	@@ -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 sha256:5f6d7bec984172381e6318c6f9a5f6028da49893f5afa6aa3baeecccaf730ded
+size 1646571552

+version https://git-lfs.github.com/spec/v1
+oid sha256:76df432310864f3ab411033c222d0bc7928223db2cc48679d9b44e8d6548cbfa
+size 3093667872