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

-----------------------------------------------
- Update August 14th 2026 -
-----------------------------------------------

• New chat template! Yes, a new chat template that completely fixes previous issues for llama.cpp users
  and retains higher performance than the originally made template for Ollama/Yollama users!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
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:
(This template features a sliding context window of TWENTY-NINE (29) messages.
This can be adjusted per-individual requirements simply by altering
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 -%}

------------------------------------------------
- Model Details and Specifications: -
------------------------------------------------

Ministral-3 3B Instruct 2512 (GGUF)

This release contains:
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
  (by MistralAI)

Original Model Link:

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

---

-------------------------------------------------------------
- GGUF Conversion and Quantization Details: -
-------------------------------------------------------------

Software used to convert Safetensors to GGUF:

• llama.cpp

Software used to create Quantized GGUF Files:

• llama.cpp

Specific GitHub Commit Point:

• b7540

Converted to GGUF and Quantized by:

• EnlistedGhost

---

--------------------------
---- Original Info ----
--------------------------

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

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	0.850	0.898	0.712	0.646
Qwen3-14B (Thinking)	0.737	0.837	0.663	0.593
Ministral 3 8B	0.787	0.860	0.668	0.616
Qwen3-VL-8B-Thinking	0.798	0.860	0.671	0.580
Ministral 3 3B	0.721	0.775	0.534	0.548
Qwen3-VL-4B-Thinking	0.697	0.729	0.601	0.513

Instruct

Model	Arena Hard	WildBench	MATH Maj@1	MM MTBench
Ministral 3 14B	0.551	68.5	0.904	8.49
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	66.8	0.876	8.08
Qwen3-VL-8B-Instruct	0.528	66.3	0.946	8.00
Ministral 3 3B	0.305	56.8	0.830	7.83
Qwen3-VL-4B-Instruct	0.438	56.8	0.900	8.01
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	0.676	0.648	0.820	0.794	0.749
Qwen3 14B Base	0.754	0.620	0.661	0.837	0.804	0.703
Gemma 3 12B Base	0.690	0.487	0.587	0.766	0.745	0.788
Ministral 3 8B	0.706	0.626	0.591	0.793	0.761	0.681
Qwen 3 8B Base	0.700	0.576	0.596	0.794	0.760	0.639
Ministral 3 3B	0.652	0.601	0.511	0.735	0.707	0.592
Qwen 3 4B Base	0.677	0.405	0.570	0.759	0.713	0.530
Gemma 3 4B Base	0.516	0.294	0.430	0.626	0.589	0.640

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.