Downloads · 30 days
20
2% of all-time downloads
kloseli/MiniMax-M2.1-REAP-30-mlx-mxfp4
MiniMax-M2.1-REAP-30-mlx-mxfp4 is a text generation model from kloseli. Use it when you need the model to write or continue text. It is set up for mlx. The card lists the license as apache-2.0.
This model kloseli/MiniMax-M2.1-REAP-30-mlx-mxfp4 was converted to MLX format from 0xSero/MiniMax-M2.1-REAP-30 using mlx-lm version 0.30.2.
Downloads · 30 days
20
2% of all-time downloads
All-time downloads
1K
Public
Parameters
162B
86.1 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors86.1 GB · 100%
How the weights are stored.
U32162B · 100%
From the Hugging Face model README
This model kloseli/MiniMax-M2.1-REAP-30-mlx-mxfp4 was converted to MLX format from 0xSero/MiniMax-M2.1-REAP-30 using mlx-lm version 0.30.2.
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("kloseli/MiniMax-M2.1-REAP-30-mlx-mxfp4")
prompt = "hello"
if tokenizer.chat_template is not None:
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
messages, add_generation_prompt=True, return_dict=False,
)
response = generate(model, tokenizer, prompt=prompt, verbose=True)