Toots' MLX Quants
Collection
Various MLX quants for testing on Mac systems.
•
24 items
•
Updated
The Model mrtoots/Wayfarer-2-12B-mlx-8Bit was converted to MLX format from LatitudeGames/Wayfarer-2-12B using mlx-lm version 0.26.4.
Please follow and support LatitudeGames' work if you like it!
🦛 If you want a free consulting session, fill out this form to get in touch! 🤗
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("mrtoots/Wayfarer-2-12B-mlx-8Bit")
prompt="hello"
if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
messages, tokenize=False, add_generation_prompt=True
)
response = generate(model, tokenizer, prompt=prompt, verbose=True)
Base model
mistralai/Mistral-Nemo-Base-2407