Polaris-4B-Preview-dwq3-mlx

This model Polaris-4B-Preview-dwq3-mlx was converted to MLX format from POLARIS-Project/Polaris-4B-Preview using mlx-lm version 0.26.0.

Use with mlx

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("Polaris-4B-Preview-dwq3-mlx")

prompt = "hello"

if tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)
Downloads last month
7
Safetensors
Model size
629M params
Tensor type
BF16
·
U32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for nightmedia/Polaris-4B-Preview-dwq3-mlx

Base model

Qwen/Qwen3-4B-Base
Finetuned
Qwen/Qwen3-4B
Quantized
(18)
this model

Collection including nightmedia/Polaris-4B-Preview-dwq3-mlx