---

license: apache-2.0

datasets:

• mistralai/MM-MT-Bench

language:

• en
• fr
• es
• de
• it
• pt
• nl
• zh
• ja
• ko
• ar

base_model:

• mistralai/Ministral-3-3B-Instruct-2512-BF16

new_version: EnlistedGhost/Ministral-3-3B-Instruct-2512-GGUF

pipeline_tag: image-text-to-text

tags:

• MistralAI
• Ministral
• Ministral-3
• Ollama
• Llama.cpp
• GGUF
• Image-Text-to-Text
• Conversational
• Quantize
• Multimodal
• Mistral3

---

<img src="https://ollama.com/assets/library/mistral-nemo/72045292-694a-4867-88c8-8635c9d97030" alt="Example image" width="168" height="128">

<img src="https://ollama.com/assets/library/ministral-3/83fa3859-d87f-492c-bd81-596cfbceeccb" alt="Example image" width="64" height="64">

-----------------------------------------------<br /> - Update August 14th 2026 -<br />-----------------------------------------------

• New chat template! Yes, a new chat template that completely fixes previous issues for llama.cpp users <br />and retains higher performance than the originally made template for Ollama/Yollama users!
• Fixed both F16 and F32 MMPROJ Multi-Modal Vision projectors. (Re-Uploaded with working projectors)
• Uploaded custom, high-quality, new "GH05T" edition Quant files for this model!

(This is a brand new method I have been developing for some time, I sincerely hope you enjoy it!)

Custom GH05T Quants Added:

*These offer significantly higher performance and quality of response over previously uploaded release files while remaining <br />

similar or smaller in size!*

• IQ2_M
• Q2_K_L
• IQ3_M
• Q3_K_L
• IQ4_XS
• Q4_K_M
• Q5_K_XL
• Q6_K_L
• Q8_0_L
• F16

New JINJA Tokenizer Chat-Template: <br />

(This template features a sliding context window of TWENTY-NINE (29) messages. <br /> This can be adjusted per-individual requirements simply by altering <br />the number 29 in the template higher or lower in numerical value)

{%- set ns = namespace(remMessage=false, hasSys=false, injSystem=true) -%}
{%- for msg in messages -%}
	{%- if msg.role == "system" -%}
		{%- set ns.hasSys = true -%}
	{%- endif -%}
{%- endfor -%}
{%- for msg in messages -%}
	{{- bos_token }}
	{%- if ns.injSystem -%}
		[SYSTEM_PROMPT]
		{%- if ns.hasSys -%}
			{{ msg.content }}
		{%- else -%}
			'Follow instructions the user provides... (System Prompt)'
		{%- endif -%}
		[/SYSTEM_PROMPT]
		{%- set ns.injSystem = false -%}
	{%- endif -%}
	{%- if (messages|length - loop.index0) < 29 -%}
		{%- set ns.remMessage = true -%}
	{%- endif -%}
	{%- if ns.remMessage -%}
		{%- if msg.role == "user" -%}
			{{- '[INST]' }}
			{%- if msg.content is string %}
				{{ msg.content }}
        	{%- else %}
            	{%- for block in msg.content %}
            		{%- if block.type == 'text' %}
                    	{{- block.text }}
                	{%- elif block.type in ['image', 'image_url'] %}
                    	{{- '[IMG]' }}
                	{%- endif %}
            	{%- endfor %}
            {%- endif %}
            {{- '[/INST]' }}
		{%- elif msg.role == "assistant" -%}
			{{ msg.content }}
		{%- endif -%}
	{%- endif -%}
	{{- eos_token }}
{%- endfor -%}

------------------------------------------------<br /> - Model Details and Specifications: -<br />------------------------------------------------

Ministral-3 3B Instruct 2512 (GGUF)

This release contains: <br />

GGUF converted and Quantized model files

(Compatible with:)

• Yollama - Privacy and Security Rewrite of Ollama
• Llama.cpp
• Ollama

Quantized GGUF version of:

• Ministral-3-3B-Instruct-2512-BF16 <br /> (by MistralAI)

Original Model Link:

• mistralai/Ministral-3-3B-Instruct-2512-BF16

----------------------------------------------

-------------------------------------------------------------<br /> - GGUF Conversion and Quantization Details: -<br />-------------------------------------------------------------

Software used to convert Safetensors to GGUF:

• <a href="https://github.com/ggml-org/llama.cpp/">llama.cpp</a>

Software used to create Quantized GGUF Files:

• <a href="https://github.com/ggml-org/llama.cpp/">llama.cpp</a>

Specific GitHub Commit Point:

• <a href="https://github.com/ggml-org/llama.cpp/commit/85c40c9b02941ebf1add1469af75f1796d513ef4">b7540</a>

Converted to GGUF and Quantized by:

• EnlistedGhost

----------------------------------------------

--------------------------<br /> ---- Original Info ---- <br /> --------------------------

(Crossposted from the link in the above section: "Model Details"):

<br />

<br />

<br />

<br />

Ministral 3 14B Instruct 2512 BF16

The largest model in the Ministral 3 family, Ministral 3 14B offers frontier capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart. A powerful and efficient 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 14B can even be deployed locally, capable of fitting in 32GB of VRAM in BF16, and less than 24GB 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.

Key Features

Ministral 3 14B consists of two main architectural components:

• 13.5B Language Model
• 0.4B Vision Encoder

The Ministral 3 14B 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

Private AI deployments where advanced capabilities meet practical hardware constraints:

• Private/custom chat and AI assistant deployments in constrained environments
• Advanced local agentic use cases
• Fine-tuning and specialization
• And more...

Bringing advanced AI capabilities to most environments.

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.