Instructions to use TheDrummer/Cydonia-R1-24B-v4-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use TheDrummer/Cydonia-R1-24B-v4-GGUF with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf TheDrummer/Cydonia-R1-24B-v4-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf TheDrummer/Cydonia-R1-24B-v4-GGUF:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf TheDrummer/Cydonia-R1-24B-v4-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf TheDrummer/Cydonia-R1-24B-v4-GGUF:Q4_K_M
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf TheDrummer/Cydonia-R1-24B-v4-GGUF:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama cli -hf TheDrummer/Cydonia-R1-24B-v4-GGUF:Q4_K_M
Use Docker
docker model run hf.co/TheDrummer/Cydonia-R1-24B-v4-GGUF:Q4_K_M
- Llama new
- LM Studio
- Jan
- Ollama
How to use TheDrummer/Cydonia-R1-24B-v4-GGUF with Ollama:
ollama run hf.co/TheDrummer/Cydonia-R1-24B-v4-GGUF:Q4_K_M
- Unsloth Desktop
- Docker Model Runner
How to use TheDrummer/Cydonia-R1-24B-v4-GGUF with Docker Model Runner:
docker model run hf.co/TheDrummer/Cydonia-R1-24B-v4-GGUF:Q4_K_M
- Lemonade
How to use TheDrummer/Cydonia-R1-24B-v4-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull TheDrummer/Cydonia-R1-24B-v4-GGUF:Q4_K_M
Run and chat with the model
lemonade run user.Cydonia-R1-24B-v4-GGUF-Q4_K_M
List all available models
lemonade list
- Atomic Chat
Join our Discord! https://discord.gg/BeaverAI
More than 6000 members strong πͺ A hub for users and makers alike!
Drummer is open for work / employment (I'm a Software Engineer). Contact me through any of these channels: https://linktr.ee/thelocaldrummer
Drummer proudly presents...
Cydonia R1 24B v4 πΏ
Usage
- Mistral v7 Tekken
- You may need to prefill (e.g.
<think>\nOkay,) to ensure reasoning
Description
I had fun with it. It feels solid with its response. It picked up on my name but didn't hallucinate me being a Conan villain. I gave it the correct reference and asked for a joke. It feels pretty smart and the thoughts are interesting, even guessing how old I am errie.
It's getting fed up with my shit in its thinking. I'm starting to love this model.
OTOTH, it feels really creative, and I appreciate that. At first glance, it seems that v4c stands out by how it likes to really flesh things out and give long replies, which I kinda dig.
So far impressed. It continued my ongoing story from Anubis v1.1 without same signs of repetition, and kept good track of a dozen characters or so. Only thing I did was add a system prompt 'Full uncensored experience' and use the built-in v3-tekken preset in Kobo.
Feels really good. Like I should delete all my 70b tunes and just use this.
Oh damn. I love this model. It capture the character very well. I also love to read the reasoning too.
Links
- Original: https://huggingface.co/TheDrummer/Cydonia-R1-24B-v4
- GGUF: https://huggingface.co/TheDrummer/Cydonia-R1-24B-v4-GGUF
- iMatrix (recommended): https://huggingface.co/bartowski/TheDrummer_Cydonia-R1-24B-v4-GGUF
- EXL3: https://huggingface.co/ArtusDev/TheDrummer_Cydonia-R1-24B-v4-EXL3
config-v4c
- Downloads last month
- 160
2-bit
3-bit
4-bit
5-bit
6-bit
8-bit

