Downloads · 30 days
24
9% of all-time downloads
Mistral-Small-3.2-24B-Instruct-2506-MLX-2bit
alankessler/Mistral-Small-3.2-24B-Instruct-2506-MLX-2bit
Mistral-Small-3.2-24B-Instruct-2506-MLX-2bit is a machine learning model from alankessler. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for mlx. The card lists the license as apache-2.0.
MLX quantized version of Mistral Small 3.2 24B Instruct 2506.
All-time downloads
279
Public
Parameters
23.6B
7.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors7.4 GB · 99%
Parameter types
How the weights are stored.
U3223.6B · 100%
Base models
Model card
From the Hugging Face model README
Mistral-Small-3.2-24B-Instruct-2506-MLX-2bit
MLX quantized version of Mistral Small 3.2 24B Instruct 2506.
Quantization
- Method: Q2 (2-bit integer quantization)
- Bits per weight: 2
- Details: Uniform 2-bit integer quantization with group size 64.
- Converted with: mlx-lm
Usage
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("alankessler/Mistral-Small-3.2-24B-Instruct-2506-MLX-2bit")
prompt = tokenizer.apply_chat_template(
[{"role": "user", "content": "Hello!"}],
add_generation_prompt=True,
tokenize=False,
)
response = generate(model, tokenizer, prompt=prompt, max_tokens=512)
print(response)
Base Model
- Model: Mistral Small 3.2 24B Instruct 2506
- Parameters: 24B
- Architecture: Mistral Small 3.2
- License: Apache 2.0
- Library
- mlx
- Type
- mistral3
- License
- apache-2.0
- Created
- Mar 11, 2026
- Updated
- Mar 11, 2026