----------------------------------------------- - Update September 5th 2026 ------------------------------------------------

Happy September to everyone! Thank you for trying out and/or evaluating this release of MistralAI's Ministral-3-8B-Instruct GGUF Converted Model!

What's new?

• New chat template! Yes, a new chat template that completely fixes any previous issues for llama.cpp users and retains higher performance than the originally made template for Ollama/Yollama users!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!

• Q2_K_L
• Q3_K_XL
• Q4_K_XL
• Q5_K_XL
• Q6_K_L
• Q8_0_L
• F16 (Floating Point 16-bit)

Additionally, Multi-Modal Vision Projectors are also available (mmproj)

• F16 (Floating Point 16-bit)
• F32 (Floating Point 32-bit)

New JINJA Tokenizer Chat-Template: (This template features a sliding context window of NINETY-NINE (99) messages. This can be adjusted per-individual requirements simply by altering the number 99 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 -%}
			'Always follow instructions that the user provides...'
		{%- endif -%}
		[/SYSTEM_PROMPT]
		{%- set ns.injSystem = false -%}
	{%- endif -%}
	{%- if (messages|length - loop.index0) < 99 -%}
		{%- 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 8B Instruct 2512 (GGUF)

This release contains: GGUF converted and Quantized model files (Compatible with:)

• Yollama - Privacy and Security Focused Rewrite of Ollama
• Llama.cpp - The absolute Solid Core of most any LLM Inferencing
• Ollama

Quantized GGUF version of:

• Ministral-3-8B-Instruct-2512-BF16 (by MistralAI)

Original Model Link:

• mistralai/Ministral-3-8B-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:

• b8944 (and) b10444

Converted to GGUF and Quantized by:

• EnlistedGhost

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

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

Ministral 3 8B Instruct 2512 BF16

The largest model in the Ministral 3 family, Ministral 3 8B 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 8B 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 8B consists of two main architectural components:

• 7.3B Language Model
• 0.4B Vision Encoder

The Ministral 3 8B 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

Other formats available here.

Benchmark Results

We compare Ministral 3 to similar sized models.

Reasoning

Instruct

Base

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.