Downloads · 30 days
22
4% of all-time downloads
Mistral-Small-3.1-24B-Base-2503-4bit
Siarhei/Mistral-Small-3.1-24B-Base-2503-4bit
Mistral-Small-3.1-24B-Base-2503-4bit is a text generation model from Siarhei. 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 Mistral-Small-3.1-24B-Base-2503-4bit was converted to MLX format from mistralai/Mistral-Small-3.1-24B-Base-2503 using mlx-lm version 0.31.1.
All-time downloads
557
Public
Parameters
23.6B
13.3 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors13.3 GB · 100%
Parameter types
How the weights are stored.
U3223.6B · 100%
Try a prompt
Base models
Model card
From the Hugging Face model README
Mistral-Small-3.1-24B-Base-2503-4bit
This model Mistral-Small-3.1-24B-Base-2503-4bit was converted to MLX format from mistralai/Mistral-Small-3.1-24B-Base-2503 using mlx-lm version 0.31.1.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("Mistral-Small-3.1-24B-Base-2503-4bit")
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
- mistral3
- License
- apache-2.0
- Languages
- en, fr, de, es, pt, it
- Created
- Mar 30, 2026
- Updated
- Mar 30, 2026