Instructions to use BeaverAI/Fallen-Mistral-R1-24B-v1c-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use BeaverAI/Fallen-Mistral-R1-24B-v1c-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="BeaverAI/Fallen-Mistral-R1-24B-v1c-GGUF",
	filename="Fallen-Mistral-R1-24B-v1c-Q2_K.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 BeaverAI/Fallen-Mistral-R1-24B-v1c-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf BeaverAI/Fallen-Mistral-R1-24B-v1c-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf BeaverAI/Fallen-Mistral-R1-24B-v1c-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 BeaverAI/Fallen-Mistral-R1-24B-v1c-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf BeaverAI/Fallen-Mistral-R1-24B-v1c-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 BeaverAI/Fallen-Mistral-R1-24B-v1c-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf BeaverAI/Fallen-Mistral-R1-24B-v1c-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 BeaverAI/Fallen-Mistral-R1-24B-v1c-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf BeaverAI/Fallen-Mistral-R1-24B-v1c-GGUF:Q4_K_M

Use Docker

docker model run hf.co/BeaverAI/Fallen-Mistral-R1-24B-v1c-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use BeaverAI/Fallen-Mistral-R1-24B-v1c-GGUF with Ollama:
```
ollama run hf.co/BeaverAI/Fallen-Mistral-R1-24B-v1c-GGUF:Q4_K_M
```

Unsloth Studio

How to use BeaverAI/Fallen-Mistral-R1-24B-v1c-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 BeaverAI/Fallen-Mistral-R1-24B-v1c-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 BeaverAI/Fallen-Mistral-R1-24B-v1c-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for BeaverAI/Fallen-Mistral-R1-24B-v1c-GGUF to start chatting

Docker Model Runner
How to use BeaverAI/Fallen-Mistral-R1-24B-v1c-GGUF with Docker Model Runner:
```
docker model run hf.co/BeaverAI/Fallen-Mistral-R1-24B-v1c-GGUF:Q4_K_M
```

Lemonade

How to use BeaverAI/Fallen-Mistral-R1-24B-v1c-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull BeaverAI/Fallen-Mistral-R1-24B-v1c-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Fallen-Mistral-R1-24B-v1c-GGUF-Q4_K_M

List all available models

lemonade list

Amazing!

by Johnae2 - opened May 1, 2025

Discussion

Johnae2

May 1, 2025

This model is really good, super creative, and has a fun writing style. Probably the best Mistral 3.1 finetune I’ve tested so far, there are a few small coherence issues here and there, but overall it’s great, it really captures the essence of the characters from the lorebook and adds details in a way I’ve never seen before, that’s what I liked the most!

TheDrummer

BeaverAI org May 2, 2025

Thanks! This fell off my radar. Will look into it. Did you try the thinking capability or no?

Johnae2

May 3, 2025

I tested the thinking capability, but I couldn’t get good results from it. Not sure if I set something up wrong, but it keeps giving me responses where the thinking never really follows the story based on my actions and ends up doing both the narrator’s and the user’s actions. But outside of thinking, the model is wunderbar!

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment