Instructions to use TheDrummer/Cydonia-24B-v3-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TheDrummer/Cydonia-24B-v3-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="TheDrummer/Cydonia-24B-v3-GGUF",
	filename="Cydonia-24B-v3e-Q2_K.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use TheDrummer/Cydonia-24B-v3-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf TheDrummer/Cydonia-24B-v3-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf TheDrummer/Cydonia-24B-v3-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 TheDrummer/Cydonia-24B-v3-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf TheDrummer/Cydonia-24B-v3-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 TheDrummer/Cydonia-24B-v3-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf TheDrummer/Cydonia-24B-v3-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 TheDrummer/Cydonia-24B-v3-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf TheDrummer/Cydonia-24B-v3-GGUF:Q4_K_M

Use Docker

docker model run hf.co/TheDrummer/Cydonia-24B-v3-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use TheDrummer/Cydonia-24B-v3-GGUF with Ollama:
```
ollama run hf.co/TheDrummer/Cydonia-24B-v3-GGUF:Q4_K_M
```

Unsloth Studio

How to use TheDrummer/Cydonia-24B-v3-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 TheDrummer/Cydonia-24B-v3-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 TheDrummer/Cydonia-24B-v3-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for TheDrummer/Cydonia-24B-v3-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use TheDrummer/Cydonia-24B-v3-GGUF with Docker Model Runner:
```
docker model run hf.co/TheDrummer/Cydonia-24B-v3-GGUF:Q4_K_M
```

Lemonade

How to use TheDrummer/Cydonia-24B-v3-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull TheDrummer/Cydonia-24B-v3-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Cydonia-24B-v3-GGUF-Q4_K_M

List all available models

lemonade list

BeaverAI

More than 5000 members strong 💪 Now with more channels! A hub for users and makers alike!

Drummer proudly presents...

Cydonia 24B v3 💿

Come ride with me through the veins of history.

Supported Chat Templates

Mistral v7 Tekken

Description

It played all my usual character cards really well.

Follows prompts well. adheres to characters nicely and is fun to RP with. it also as expected writes really nice smu7.

Creative and I'm not seeing any repetition problems, not sure how to judge intelligence in RP

Also, this model slaps. I've run it through 3rd person, 2nd person, and 1st person contexts with better than average results. It follows instructions and history well, and the prose is good. DnD DM scenario is good, keeps decent track of OOC and IC separation. Follows WI entries (I only use dictionary style though). I use non-standard system prompts and it adapts to these well. Does well on example config files for programs I use. Enough for teaching familiarization. Refusals are minimal. They happen in assistant contexts but only for extreme things. This is a great sign. Overall it feels like Cydonia22 but better. Great job spaceman!

Plans

Cydonia 24B v3.1 with more creativity and fallen influence
Skyfall 31B v3, like v2 but fits better!

Special Thanks

Thank you to each and everyone who donated and subscribed in Patreon and Ko-Fi to make our venture a little bit easier.
Subscribe to my Patreon!

Model tree for TheDrummer/Cydonia-24B-v3-GGUF

Base model

mistralai/Mistral-Small-3.1-24B-Base-2503

Finetuned

mistralai/Mistral-Small-3.1-24B-Instruct-2503

Quantized

(60)

this model

TheDrummer
/

Cydonia-24B-v3-GGUF