chore(model gallery): Add Ministral 3 family of models (aside from base versions)

gallery/index.yaml

@@ -31,7 +31,7 @@
       - "offload_to_cpu:false"
       - "offload_dit_to_cpu:false"
       - "init_lm:true"
       - "lm_model_path:acestep-5Hz-lm-0.6B" # or acestep-5Hz-lm-4B
       - "lm_backend:pt"
       - "temperature:0.85"
       - "top_p:0.9"
@@ -264,7 +264,7 @@
     known_usecases:
       - tts
     tts:
       voice: Aiden # Available speakers: Vivian, Serena, Uncle_Fu, Dylan, Eric, Ryan, Aiden, Ono_Anna, Sohee
     parameters:
       model: Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice
 - !!merge <<: *qwen-tts
@@ -276,7 +276,7 @@
     known_usecases:
       - tts
     tts:
       voice: Aiden # Available speakers: Vivian, Serena, Uncle_Fu, Dylan, Eric, Ryan, Aiden, Ono_Anna, Sohee
     parameters:
       model: Qwen/Qwen3-TTS-12Hz-0.6B-CustomVoice
 - &qwen-asr
@@ -4317,7 +4317,7 @@
     - gemma3
     - gemma-3
   overrides:
     #mmproj: gemma-3-27b-it-mmproj-f16.gguf
     parameters:
       model: gemma-3-27b-it-Q4_K_M.gguf
   files:
@@ -4335,7 +4335,7 @@
   description: |
     google/gemma-3-12b-it is an open-source, state-of-the-art, lightweight, multimodal model built from the same research and technology used to create the Gemini models. It is capable of handling text and image input and generating text output. It has a large context window of 128K tokens and supports over 140 languages. The 12B variant has been fine-tuned using the instruction-tuning approach. Gemma 3 models are suitable for a variety of text generation and image understanding tasks, including question answering, summarization, and reasoning. Their relatively small size makes them deployable in environments with limited resources such as laptops, desktops, or your own cloud infrastructure.
   overrides:
     #mmproj: gemma-3-12b-it-mmproj-f16.gguf
     parameters:
       model: gemma-3-12b-it-Q4_K_M.gguf
   files:
@@ -4353,7 +4353,7 @@
   description: |
     Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models. Gemma 3 models are multimodal, handling text and image input and generating text output, with open weights for both pre-trained variants and instruction-tuned variants. Gemma 3 has a large, 128K context window, multilingual support in over 140 languages, and is available in more sizes than previous versions. Gemma 3 models are well-suited for a variety of text generation and image understanding tasks, including question answering, summarization, and reasoning. Their relatively small size makes it possible to deploy them in environments with limited resources such as laptops, desktops or your own cloud infrastructure, democratizing access to state of the art AI models and helping foster innovation for everyone. Gemma-3-4b-it is a 4 billion parameter model.
   overrides:
     #mmproj: gemma-3-4b-it-mmproj-f16.gguf
     parameters:
       model: gemma-3-4b-it-Q4_K_M.gguf
   files:
@@ -7571,7 +7571,7 @@
       sha256: 2756551de7d8ff7093c2c5eec1cd00f1868bc128433af53f5a8d434091d4eb5a
       uri: huggingface://Triangle104/Nano_Imp_1B-Q8_0-GGUF/nano_imp_1b-q8_0.gguf
 - &smollm
   url: "github:mudler/LocalAI/gallery/chatml.yaml@master" ## SmolLM
   name: "smollm-1.7b-instruct"
   icon: https://huggingface.co/datasets/HuggingFaceTB/images/resolve/main/banner_smol.png
   tags:
@@ -7615,7 +7615,7 @@
       sha256: decd2598bc2c8ed08c19adc3c8fdd461ee19ed5708679d1c54ef54a5a30d4f33
       uri: huggingface://HuggingFaceTB/SmolLM2-1.7B-Instruct-GGUF/smollm2-1.7b-instruct-q4_k_m.gguf
 - &llama31
   url: "github:mudler/LocalAI/gallery/llama3.1-instruct.yaml@master" ## LLama3.1
   icon: https://avatars.githubusercontent.com/u/153379578
   name: "meta-llama-3.1-8b-instruct"
   license: llama3.1
@@ -12398,6 +12398,311 @@
     - filename: llama-cpp/mmproj/mmproj-mistral-community_pixtral-12b-f16.gguf
       sha256: a0b21e5a3b0f9b0b604385c45bb841142e7a5ac7660fa6a397dbc87c66b2083e
       uri: huggingface://bartowski/mistral-community_pixtral-12b-GGUF/mmproj-mistral-community_pixtral-12b-f16.gguf
+- !!merge <<: *mistral03
+  name: "mistralai_ministral-3-14b-instruct-2512-multimodal"
+  urls:
+    - https://huggingface.co/mistralai/Ministral-3-14B-Instruct-2512
+    - https://huggingface.co/unsloth/Ministral-3-14B-Instruct-2512-GGUF
+  description: |
+    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.
+
+    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 24GB of VRAM in FP8, and less if further quantized.
+
+    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.
+
+    This gallery entry includes mmproj for multimodality and uses Unsloth recommended defaults.
+  tags:
+    - llm
+    - gguf
+    - gpu
+    - mistral
+    - cpu
+    - function-calling
+    - multimodal
+  overrides:
+    context_size: 16384
+    parameters:
+      model: llama-cpp/models/mistralai_Ministral-3-14B-Instruct-2512-Q4_K_M.gguf
+      temperature: 0.15
+    mmproj: llama-cpp/mmproj/mmproj-mistralai_Ministral-3-14B-Instruct-2512-f32.gguf
+  files:
+    - filename: llama-cpp/models/mistralai_Ministral-3-14B-Instruct-2512-Q4_K_M.gguf
+      sha256: 76ce697c065f2e40f1e8e958118b02cab38e2c10a6015f7d7908036a292dc8c8
+      uri: huggingface://unsloth/Ministral-3-14B-Instruct-2512-GGUF/Ministral-3-14B-Instruct-2512-Q4_K_M.gguf
+    - filename: llama-cpp/mmproj/mmproj-mistralai_Ministral-3-14B-Instruct-2512-f32.gguf
+      sha256: 2740ba9e9b30b09be4282a9a9f617ec43dc47b89aed416cb09b5f698f90783b5
+      uri: huggingface://unsloth/Ministral-3-14B-Instruct-2512-GGUF/mmproj-F32.gguf
+- !!merge <<: *mistral03
+  name: "mistralai_ministral-3-14b-reasoning-2512-multimodal"
+  urls:
+    - https://huggingface.co/mistralai/Ministral-3-14B-Reasoning-2512
+    - https://huggingface.co/unsloth/Ministral-3-14B-Reasoning-2512-GGUF
+  description: |
+    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 reasoning post-trained version, trained for reasoning tasks, making it ideal for math, coding and stem related 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.
+
+    Key Features:
+    Ministral 3 14B consists of two main architectural components:
+
+
+        - 13.5B Language Model
+        - 0.4B Vision Encoder
+
+    The Ministral 3 14B Reasoning 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.
+        - Reasoning: Excels at complex, multi-step reasoning and dynamic problem-solving.
+        - 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.
+
+
+    This gallery entry includes mmproj for multimodality and uses Unsloth recommended defaults.
+  tags:
+    - llm
+    - gguf
+    - gpu
+    - mistral
+    - cpu
+    - function-calling
+    - multimodal
+  overrides:
+    context_size: 32768
+    parameters:
+      model: llama-cpp/models/mistralai_Ministral-3-14B-Reasoning-2512-Q4_K_M.gguf
+      temperature: 0.7
+      top_p: 0.95
+    mmproj: llama-cpp/mmproj/mmproj-mistralai_Ministral-3-14B-Reasoning-2512-f32.gguf
+  files:
+    - filename: llama-cpp/models/mistralai_Ministral-3-14B-Reasoning-2512-Q4_K_M.gguf
+      sha256: f577390559b89ebdbfe52cc234ea334649c24e6003ffa4b6a2474c5e2a47aa17
+      uri: huggingface://unsloth/Ministral-3-14B-Reasoning-2512-GGUF/Ministral-3-14B-Reasoning-2512-Q4_K_M.gguf
+    - filename: llama-cpp/mmproj/mmproj-mistralai_Ministral-3-14B-Reasoning-2512-f32.gguf
+      sha256: 891bf262a032968f6e5b3d4e9ffc84cf6381890033c2f5204fbdf4817af4ab9b
+      uri: huggingface://unsloth/Ministral-3-14B-Reasoning-2512-GGUF/mmproj-F32.gguf
+- !!merge <<: *mistral03
+  name: "mistralai_ministral-3-8b-instruct-2512-multimodal"
+  urls:
+    - https://huggingface.co/mistralai/Ministral-3-8B-Instruct-2512
+    - https://huggingface.co/unsloth/Ministral-3-8B-Instruct-2512-GGUF
+  description: |
+    A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.
+
+    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 12GB of VRAM in FP8, and less if further quantized.
+
+    Key Features:
+    Ministral 3 8B consists of two main architectural components:
+
+        - 8.4B 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.
+
+    This gallery entry includes mmproj for multimodality and uses Unsloth recommended defaults.
+  tags:
+    - llm
+    - gguf
+    - gpu
+    - mistral
+    - cpu
+    - function-calling
+    - multimodal
+  overrides:
+    context_size: 16384
+    parameters:
+      model: llama-cpp/models/mistralai_Ministral-3-8B-Instruct-2512-Q4_K_M.gguf
+      temperature: 0.15
+    mmproj: llama-cpp/mmproj/mmproj-mistralai_Ministral-3-8B-Instruct-2512-f32.gguf
+  files:
+    - filename: llama-cpp/models/mistralai_Ministral-3-8B-Instruct-2512-Q4_K_M.gguf
+      sha256: 5dbc3647eb563b9f8d3c70ec3d906cce84b86bb35c5e0b8a36e7df3937ab7174
+      uri: huggingface://unsloth/Ministral-3-8B-Instruct-2512-GGUF/Ministral-3-8B-Instruct-2512-Q4_K_M.gguf
+    - filename: llama-cpp/mmproj/mmproj-mistralai_Ministral-3-8B-Instruct-2512-f32.gguf
+      sha256: 242d11ff65ef844b0aac4e28d4b1318813370608845f17b3ef5826fd7e7fd015
+      uri: huggingface://unsloth/Ministral-3-8B-Instruct-2512-GGUF/mmproj-F32.gguf
+- !!merge <<: *mistral03
+  name: "mistralai_ministral-3-8b-reasoning-2512-multimodal"
+  urls:
+    - https://huggingface.co/mistralai/Ministral-3-8B-Reasoning-2512
+    - https://huggingface.co/unsloth/Ministral-3-8B-Reasoning-2512-GGUF
+  description: |
+    A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.
+
+    This model is the reasoning post-trained version, trained for reasoning tasks, making it ideal for math, coding and stem related 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 24GB of VRAM in BF16, and less than 12GB of RAM/VRAM when quantized.
+
+    Key Features:
+    Ministral 3 8B consists of two main architectural components:
+
+
+        - 8.4B Language Model
+        - 0.4B Vision Encoder
+
+    The Ministral 3 8B Reasoning 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.
+        - Reasoning: Excels at complex, multi-step reasoning and dynamic problem-solving.
+        - 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.
+
+    This gallery entry includes mmproj for multimodality and uses Unsloth recommended defaults.
+  tags:
+    - llm
+    - gguf
+    - gpu
+    - mistral
+    - cpu
+    - function-calling
+    - multimodal
+  overrides:
+    context_size: 32768
+    parameters:
+      model: llama-cpp/models/mistralai_Ministral-3-8B-Reasoning-2512-Q4_K_M.gguf
+      temperature: 0.7
+      top_p: 0.95
+    mmproj: llama-cpp/mmproj/mmproj-mistralai_Ministral-3-8B-Reasoning-2512-f32.gguf
+  files:
+    - filename: llama-cpp/models/mistralai_Ministral-3-8B-Reasoning-2512-Q4_K_M.gguf
+      sha256: c3d1c5ab7406a0fc9d50ad2f0d15d34d5693db00bf953e8a9cd9a243b81cb1b2
+      uri: huggingface://unsloth/Ministral-3-8B-Reasoning-2512-GGUF/Ministral-3-8B-Reasoning-2512-Q4_K_M.gguf
+    - filename: llama-cpp/mmproj/mmproj-mistralai_Ministral-3-8B-Reasoning-2512-f32.gguf
+      sha256: 92252621cb957949379ff81ee14b15887d37eade3845a6e937e571b98c2c84c2
+      uri: huggingface://unsloth/Ministral-3-8B-Reasoning-2512-GGUF/mmproj-F32.gguf
+- !!merge <<: *mistral03
+  name: "mistralai_ministral-3-3b-instruct-2512-multimodal"
+  urls:
+    - https://huggingface.co/mistralai/Ministral-3-3B-Instruct-2512
+    - https://huggingface.co/unsloth/Ministral-3-3B-Instruct-2512-GGUF
+  description: |
+    The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.
+
+    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 8GB of VRAM in FP8, and less if further quantized.
+
+    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.
+
+    This gallery entry includes mmproj for multimodality and uses Unsloth recommended defaults.
+  tags:
+    - llm
+    - gguf
+    - gpu
+    - mistral
+    - cpu
+    - function-calling
+    - multimodal
+  overrides:
+    context_size: 16384
+    parameters:
+      model: llama-cpp/models/mistralai_Ministral-3-3B-Instruct-2512-Q4_K_M.gguf
+      temperature: 0.15
+    mmproj: llama-cpp/mmproj/mmproj-mistralai_Ministral-3-3B-Instruct-2512-f32.gguf
+  files:
+    - filename: llama-cpp/models/mistralai_Ministral-3-3B-Instruct-2512-Q4_K_M.gguf
+      sha256: fd46fc371ff0509bfa8657ac956b7de8534d7d9baaa4947975c0648c3aa397f4
+      uri: huggingface://unsloth/Ministral-3-3B-Instruct-2512-GGUF/Ministral-3-3B-Instruct-2512-Q4_K_M.gguf
+    - filename: llama-cpp/mmproj/mmproj-mistralai_Ministral-3-3B-Instruct-2512-f32.gguf
+      sha256: 57bb4e6f01166985ca2fc16061be4023fcb95cb8e60f445b8d0bf1ee30268636
+      uri: huggingface://unsloth/Ministral-3-3B-Instruct-2512-GGUF/mmproj-F32.gguf
+- !!merge <<: *mistral03
+  name: "mistralai_ministral-3-3b-reasoning-2512-multimodal"
+  urls:
+    - https://huggingface.co/mistralai/Ministral-3-3B-Reasoning-2512
+    - https://huggingface.co/unsloth/Ministral-3-3B-Reasoning-2512-GGUF
+  description: |
+    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 reasoning post-trained version, trained for reasoning tasks, making it ideal for math, coding and stem related 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, 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 Reasoning 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.
+        - Reasoning: Excels at complex, multi-step reasoning and dynamic problem-solving.
+        - 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.
+
+    This gallery entry includes mmproj for multimodality and uses Unsloth recommended defaults.
+  tags:
+    - llm
+    - gguf
+    - gpu
+    - mistral
+    - cpu
+    - function-calling
+    - multimodal
+  overrides:
+    context_size: 32768
+    parameters:
+      model: llama-cpp/models/mistralai_Ministral-3-3B-Reasoning-2512-Q4_K_M.gguf
+      temperature: 0.7
+      top_p: 0.95
+    mmproj: llama-cpp/mmproj/mmproj-mistralai_Ministral-3-3B-Reasoning-2512-f32.gguf
+  files:
+    - filename: llama-cpp/models/mistralai_Ministral-3-3B-Reasoning-2512-Q4_K_M.gguf
+      sha256: a2648395d533b6d1408667d00e0b778f3823f3f3179ba371f89355f2e957e42e
+      uri: huggingface://unsloth/Ministral-3-3B-Reasoning-2512-GGUF/Ministral-3-3B-Reasoning-2512-Q4_K_M.gguf
+    - filename: llama-cpp/mmproj/mmproj-mistralai_Ministral-3-3B-Reasoning-2512-f32.gguf
+      sha256: 8035a6a10dfc6250f50c62764fae3ac2ef6d693fc9252307c7093198aabba812
+      uri: huggingface://unsloth/Ministral-3-3B-Reasoning-2512-GGUF/mmproj-F32.gguf
 - &mudler
   url: "github:mudler/LocalAI/gallery/mudler.yaml@master" ### START mudler's LocalAI specific-models
   name: "LocalAI-llama3-8b-function-call-v0.2"