Downloads · 30 days
18
2% of all-time downloads
MiniMax-M2.5-mixed-2-8bit
m-i/MiniMax-M2.5-mixed-2-8bit
MiniMax-M2.5-mixed-2-8bit is a text generation model from m-i. Use it when you need the model to write or continue text. It is set up for mlx. The card lists the license as other.
This model m-i/MiniMax-M2.5-mixed-2-8bit was converted to MLX format from MiniMaxAI/MiniMax-M2.5 using mlx-lm version 0.30.7.
All-time downloads
1K
Public
Parameters
229B
101 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors101 GB · 100%
Parameter types
How the weights are stored.
U32229B · 100%
Try a prompt
Base models
Model card
From the Hugging Face model README
m-i/MiniMax-M2.5-mixed-2-8bit
This model m-i/MiniMax-M2.5-mixed-2-8bit was converted to MLX format from MiniMaxAI/MiniMax-M2.5 using mlx-lm version 0.30.7.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("m-i/MiniMax-M2.5-mixed-2-8bit")
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)
- Task
- Text Generation
- Library
- mlx
- Type
- minimax_m2
- License
- other
- Created
- Feb 13, 2026
- Updated
- Feb 13, 2026