Downloads · 30 days
13
7% of all-time downloads
sigjhl/phi-4-mlx-8Bit
phi-4-mlx-8Bit is a text generation model from sigjhl. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as mit.
The Model sigjhl/phi-4-mlx-8Bit was converted to MLX format from unsloth/phi-4 using mlx-lm version 0.21.5.
Downloads · 30 days
13
7% of all-time downloads
All-time downloads
174
Public
Parameters
14.7B
15.6 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors15.6 GB · 100%
How the weights are stored.
U3214.7B · 100%
From the Hugging Face model README
The Model sigjhl/phi-4-mlx-8Bit was converted to MLX format from unsloth/phi-4 using mlx-lm version 0.21.5.
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("sigjhl/phi-4-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)