Instructions to use Undi95/MistralThinker-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Undi95/MistralThinker-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Undi95/MistralThinker-GGUF",
	filename="MistralThinker.q8_0.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 Undi95/MistralThinker-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Undi95/MistralThinker-GGUF:Q8_0
# Run inference directly in the terminal:
llama-cli -hf Undi95/MistralThinker-GGUF:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Undi95/MistralThinker-GGUF:Q8_0
# Run inference directly in the terminal:
llama-cli -hf Undi95/MistralThinker-GGUF:Q8_0

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 Undi95/MistralThinker-GGUF:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf Undi95/MistralThinker-GGUF:Q8_0

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 Undi95/MistralThinker-GGUF:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Undi95/MistralThinker-GGUF:Q8_0

Use Docker

docker model run hf.co/Undi95/MistralThinker-GGUF:Q8_0

LM Studio
Jan
Ollama
How to use Undi95/MistralThinker-GGUF with Ollama:
```
ollama run hf.co/Undi95/MistralThinker-GGUF:Q8_0
```

Unsloth Studio new

How to use Undi95/MistralThinker-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 Undi95/MistralThinker-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 Undi95/MistralThinker-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Undi95/MistralThinker-GGUF to start chatting

Docker Model Runner
How to use Undi95/MistralThinker-GGUF with Docker Model Runner:
```
docker model run hf.co/Undi95/MistralThinker-GGUF:Q8_0
```

Lemonade

How to use Undi95/MistralThinker-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Undi95/MistralThinker-GGUF:Q8_0

Run and chat with the model

lemonade run user.MistralThinker-GGUF-Q8_0

List all available models

lemonade list

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

https://huggingface.co/Undi95/MistralThinker-GGUF/discussions/1

Those repo are public because I hit the private storage limit, but feel free to try. This model use the Mistral V7 prompt format.

It was trained on DeepSeek R1 RP log and character card, and some funny shit.

Default system prompt: "You are MistralThinker, a Large Language Model (LLM) created by Undi.\nYour knowledge base was last updated on 2023-10-01. Current date: {date}.\n\nWhen unsure, state you don't know."

I recommand you putting information about the persona and yourself in the system prompt to let the magic happen.

I sadly have a problem with the prompt format, in the tokenizer_config.json

I try to recreate what DeepSeek have done with their distill : they added <think> at the beginning of each assistant reply and cut off the thinking part in the context.

I did the same, but on my side, the first <think> don't appear using "Chat completion".

Other than that, the model seem fully functionnal, feel free to try, but be sure to prefill <think> one way or another.

Here's an exemple where the character card contain You're roleplaying as a hot 35 years old motherly MILF, and a custom system prompt.

Downloads last month: 19

GGUF

Model size

24B params

Architecture

llama

Hardware compatibility

8-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support