Ministral-3 3B-Base 2512
Ministral 3 3B Base 2512 is a compact multimodal foundation model from Mistral AI. It combines a 3.4B-parameter language decoder with a 0.4B frozen vision encoder for native image understanding. Distilled from the 24B Mistral Small 3.1 through an iterative “Cascade Distillation” process, it preserves much of its teacher model’s capability while supporting a 256K token context window via YaRN RoPE scaling.
Ministral-3 3B Base 2512
Summary
Introduction
The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities. This model is the base pre-trained version, not fine-tuned for instruction or reasoning tasks, making it ideal for custom post-training processes. For instruction and chat based use cases, we recommend using Ministral 3 3B Instruct 2512. The Ministral 3 family is designed for edge deployment, capable of running on a wide range of hardware. Ministral 3 3B can even be deployed locally, fitting in 16GB of VRAM in BF16, and less than 8GB of RAM/VRAM when quantized.
Key Features
Ministral 3 3B consists of two main architectural components:
- 3.4B Language Model
- 0.4B Vision Encoder
The Ministral 3 3B Base model offers the following capabilities:
- Vision: Enables the model to analyze images and provide insights based on visual content, in addition to text.
- Multilingual: Supports dozens of languages, including English, French, Spanish, German, Italian, Portuguese, Dutch, Chinese, Japanese, Korean, Arabic.
- Edge-Optimized: Delivers best-in-class performance at a small scale, deployable anywhere.
- Apache 2.0 License: Open-source license allowing usage and modification for both commercial and non-commercial purposes.
- Large Context Window: Supports a 256k context window.
Use Cases
Ideal for lightweight, real-time applications on edge or low-resource devices, such as:
- Image captioning
- Text classification
- Real-time efficient translation
- Data extraction
- Short content generation
- Fine-tuning and specialization
- And more... Bringing advanced AI capabilities to edge and distributed environments for embedded systems
Parameters
Inputs
prompt- (text): User-provided input can be a question, a request, or the context to be addressed. The system uses the prompt to analyze, infer, and generate a corresponding response.
Output
output_text- (text): The content generated after the token is the final answer that the model returns to the user.
Usage for developers
Please find below the details to track the information and access the code for processing the model on our platform.
Requirements
pip install -r requirements.txt
Code based on AIOZ structure
import os
from transformers import Mistral3ForConditionalGeneration, MistralCommonBackend
...
def do_ai_task(
prompt: Union[str, str],
model_storage_directory: Union[str, Path],
device: Literal["cpu", "cuda", "gpu"] = "cpu",
*args, **kwargs) -> Any:
"""Define AI task: load model, pre-process, post-process, etc ..."""
# Define AI task workflow. Below is an example
model_weight_path = os.path.join(model_storage_directory, "Ministral-3-3B-Base-2512")
model = Mistral3ForConditionalGeneration.from_pretrained(
model_weight_path,
device_map="auto",
)
tokenizer = MistralCommonBackend.from_pretrained(model_weight_path)
...
decoded_output = tokenizer.decode(output[len(input_ids[0]):])
return decoded_output
Reference
This repository is based on and inspired by mistralai's work. We sincerely appreciate their generosity in sharing the code.
License
We respect and comply with the terms of the author's license cited in the Reference section.