This is a JANG quantization of TheDrummer/Cydonia-24B-v4.3 using the JANG_3L preset.
You need a JANG runtime, this does not work with pure MLX.
Links
- GitHub | HuggingFace | MLX Studio | PyPI | Format Spec
- Downloads last month
- 18
Model size
24B params
Tensor type
U32
·
F16 ·
Hardware compatibility
Log In to add your hardware
Quantized
Model tree for mobbitxt/Cydonia-24B-v4.3-JANG_3L
Base model
mistralai/Mistral-Small-3.1-24B-Base-2503 Finetuned
TheDrummer/Cydonia-24B-v4.3
# Make sure mlx-lm is installed # pip install --upgrade mlx-lm # Generate text with mlx-lm from mlx_lm import load, generate model, tokenizer = load("mobbitxt/Cydonia-24B-v4.3-JANG_3L") prompt = "Write a story about Einstein" messages = [{"role": "user", "content": prompt}] prompt = tokenizer.apply_chat_template( messages, add_generation_prompt=True ) text = generate(model, tokenizer, prompt=prompt, verbose=True)