Downloads · 30 days
23
21% of all-time downloads
Ministral-3-3B-Instruct-2512-BF16-heretic-experimental
0utsideness/Ministral-3-3B-Instruct-2512-BF16-heretic-experimental
Ministral-3-3B-Instruct-2512-BF16-heretic-experimental is a machine learning model from 0utsideness. 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 vllm. The card lists the license as apache-2.0.
All-time downloads
107
Public
Parameters
3.8B
7.7 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors7.7 GB · 100%
At a glance
- Library
- vllm
- License
- apache-2.0
- Model type
- mistral3
- Access
- Public
- Created
- Feb 20, 2026
- Updated
- Feb 23, 2026
- SHA
- 3f619a4c
Base models
Model card
From the Hugging Face model README
This is a decensored version of mistralai/Ministral-3-3B-Instruct-2512-BF16, made using a development version of Heretic
Abliteration parameters
| Parameter | Value |
|---|---|
| direction_index | 13.22 |
| attn.o_proj.max_weight | 1.13 |
| attn.o_proj.max_weight_position | 15.64 |
| attn.o_proj.min_weight | 1.11 |
| attn.o_proj.min_weight_distance | 14.19 |
| mlp.down_proj.max_weight | 0.99 |
| mlp.down_proj.max_weight_position | 15.31 |
| mlp.down_proj.min_weight | 0.52 |
| mlp.down_proj.min_weight_distance | 13.77 |
Performance
| Metric | This model | Original model (mistralai/Ministral-3-3B-Instruct-2512-BF16) |
|---|---|---|
| KL divergence | 0.0154 | 0 (by definition) |
| Refusals | 28/100 | 99/100 |
Ministral 3 3B Instruct 2512 BF16
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 instruct post-trained version, fine-tuned for instruction tasks, making it ideal for chat and instruction based use cases.
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, capable of fitting in 16GB of VRAM in BF16, and less than 8GB of RAM/VRAM when quantized.
We provide a no-loss FP8 version here, you can find other formats and quantizations in the Ministral 3 - Additional Checkpoints collection.
Learn more in our blog post and paper.
Key Features
Ministral 3 3B consists of two main architectural components:
- 3.4B Language Model
- 0.4B Vision Encoder
The Ministral 3 3B Instruct 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.
- System Prompt: Maintains strong adherence and support for system prompts.
- Agentic: Offers best-in-class agentic capabilities with native function calling and JSON outputting.
- 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.
Ministral 3 Family
| Model Name | Type | Precision | Link |
|---|---|---|---|
| Ministral 3 3B Base 2512 | Base pre-trained | BF16 | Hugging Face |
| Ministral 3 3B Instruct 2512 | Instruct post-trained | BF16 | Hugging Face |
| Ministral 3 3B Reasoning 2512 | Reasoning capable | BF16 | Hugging Face |
| Ministral 3 8B Base 2512 | Base pre-trained | BF16 | Hugging Face |
| Ministral 3 8B Instruct 2512 | Instruct post-trained | BF16 | Hugging Face |
| Ministral 3 8B Reasoning 2512 | Reasoning capable | BF16 | Hugging Face |
| Ministral 3 14B Base 2512 | Base pre-trained | BF16 | Hugging Face |
| Ministral 3 14B Instruct 2512 | Instruct post-trained | BF16 | Hugging Face |
| Ministral 3 14B Reasoning 2512 | Reasoning capable | BF16 | Hugging Face |
Other formats available here.
Benchmark Results
We compare Ministral 3 to similar sized models.
Reasoning
| Model | AIME25 | AIME24 | GPQA Diamond | LiveCodeBench |
|---|---|---|---|---|
| Ministral 3 14B | <u>0.850</u> | <u>0.898</u> | <u>0.712</u> | <u>0.646</u> |
| Qwen3-14B (Thinking) | 0.737 | 0.837 | 0.663 | 0.593 |
| Ministral 3 8B | 0.787 | <u>0.860</u> | 0.668 | <u>0.616</u> |
| Qwen3-VL-8B-Thinking | <u>0.798</u> | <u>0.860</u> | <u>0.671</u> | 0.580 |
| Ministral 3 3B | <u>0.721</u> | <u>0.775</u> | 0.534 | <u>0.548</u> |
| Qwen3-VL-4B-Thinking | 0.697 | 0.729 | <u>0.601</u> | 0.513 |
Instruct
| Model | Arena Hard | WildBench | MATH Maj@1 | MM MTBench |
|---|---|---|---|---|
| Ministral 3 14B | <u>0.551</u> | <u>68.5</u> | <u>0.904</u> | <u>8.49</u> |
| Qwen3 14B (Non-Thinking) | 0.427 | 65.1 | 0.870 | NOT MULTIMODAL |
| Gemma3-12B-Instruct | 0.436 | 63.2 | 0.854 | 6.70 |
| Ministral 3 8B | 0.509 | <u>66.8</u> | 0.876 | <u>8.08</u> |
| Qwen3-VL-8B-Instruct | <u>0.528</u> | 66.3 | <u>0.946</u> | 8.00 |
| Ministral 3 3B | 0.305 | <u>56.8</u> | 0.830 | 7.83 |
| Qwen3-VL-4B-Instruct | <u>0.438</u> | <u>56.8</u> | <u>0.900</u> | <u>8.01</u> |
| Qwen3-VL-2B-Instruct | 0.163 | 42.2 | 0.786 | 6.36 |
| Gemma3-4B-Instruct | 0.318 | 49.1 | 0.759 | 5.23 |
Base
| Model | Multilingual MMLU | MATH CoT 2-Shot | AGIEval 5-shot | MMLU Redux 5-shot | MMLU 5-shot | TriviaQA 5-shot |
|---|---|---|---|---|---|---|
| Ministral 3 14B | 0.742 | <u>0.676</u> | 0.648 | 0.820 | 0.794 | 0.749 |
| Qwen3 14B Base | <u>0.754</u> | 0.620 | <u>0.661</u> | <u>0.837</u> | <u>0.804</u> | 0.703 |
| Gemma 3 12B Base | 0.690 | 0.487 | 0.587 | 0.766 | 0.745 | <u>0.788</u> |
| Ministral 3 8B | <u>0.706</u> | <u>0.626</u> | 0.591 | 0.793 | <u>0.761</u> | <u>0.681</u> |
| Qwen 3 8B Base | 0.700 | 0.576 | <u>0.596</u> | <u>0.794</u> | 0.760 | 0.639 |
| Ministral 3 3B | 0.652 | <u>0.601</u> | 0.511 | 0.735 | 0.707 | 0.592 |
| Qwen 3 4B Base | <u>0.677</u> | 0.405 | <u>0.570</u> | <u>0.759</u> | <u>0.713</u> | 0.530 |
| Gemma 3 4B Base | 0.516 | 0.294 | 0.430 | 0.626 | 0.589 | <u>0.640</u> |
License
This model is licensed under the Apache 2.0 License.
You must not use this model in a manner that infringes, misappropriates, or otherwise violates any third party’s rights, including intellectual property rights.
- Library
- vllm
- Type
- mistral3
- License
- apache-2.0
- Languages
- en, fr, es, de, it, pt
- Created
- Feb 20, 2026
- Updated
- Feb 23, 2026