from unsloth import FastModel
import torch

fourbit_models = [
    # 4bit dynamic quants for superior accuracy and low memory use
    "unsloth/gemma-3-1b-it-unsloth-bnb-4bit",
    "unsloth/gemma-3-4b-it-unsloth-bnb-4bit",
    "unsloth/gemma-3-12b-it-unsloth-bnb-4bit",
    "unsloth/gemma-3-27b-it-unsloth-bnb-4bit",

    "unsloth/Mistral-Small-3.1-24B-Instruct-2503-unsloth-bnb-4bit",
] # More models at https://huggingface.co/unsloth

model, tokenizer = FastModel.from_pretrained(
    model_name = "mistralai/Mistral-Small-3.1-24B-Instruct-2503",
#    model_name =  "unsloth/Mistral-Small-3.1-24B-Instruct-2503-unsloth-bnb-4bit", (this one too)
    max_seq_length = 2048, # Choose any for long context!
    load_in_4bit = False,  # 4 bit quantization to reduce memory
    load_in_8bit = False, # [NEW!] A bit more accurate, uses 2x memory
    full_finetuning = False, # [NEW!] We have full finetuning now!
    # token = "hf_...", # use one if using gated models
)