--- license: apache-2.0 language: - en - fr - es - de - it - pt - nl - zh - ja - ko - ar base_model: - mistralai/Ministral-3-3B-Reasoning-2512 - mistralai/Ministral-3-8B-Reasoning-2512 - mistralai/Ministral-3-14B-Reasoning-2512 library_name: transformers pipeline_tag: image-text-to-text tags: - text-generation-inference - llama.cpp - f32 --- # **Ministral-3-Reasoning-2512-AIO-GGUF** > The [Ministral 3 Reasoning](https://huggingface.co/collections/mistralai/ministral-3) models (3B, 8B, and 14B variants from mistralai) are post-trained vision-language models specialized for advanced reasoning tasks like math, coding, and STEM applications, featuring a core language model (3.4B, 8.4B, or 13.5B parameters) paired with a 0.4B vision encoder for multimodal image analysis, supporting a 256k context window, multilingual capabilities, and edge deployment on hardware as low as 24GB VRAM/RAM when quantized (BF16 precision). Optimized with a recommended temperature of 0.7 and top_p=0.95 for reasoning, they use a distinctive chat template encouraging structured [THINK] inner monologue drafts in Markdown/LaTeX before final responses, enabling step-by-step problem-solving while maintaining strong performance in benchmarks like AIME25 (0.721 for 3B) and GPQA Diamond. Ideal for resource-efficient local inference via vLLM or Transformers, these Apache 2.0-licensed models excel in agentic workflows, function calling, and complex multimodal reasoning under constrained environments. ## Ministral-3-14B-Reasoning-2512 [GGUF] | File Name | Quant Type | File Size | File Link | | - | - | - | - | | Ministral-3-14B-Reasoning-2512-BF16.gguf | BF16 | 27 GB | [Download](https://huggingface.co/prithivMLmods/Ministral-3-Reasoning-2512-AIO-GGUF/blob/main/Ministral-3-14B-Reasoning-2512-BF16.gguf) | | Ministral-3-14B-Reasoning-2512-Q4_K_M.gguf | Q4_K_M | 8.24 GB | [Download](https://huggingface.co/prithivMLmods/Ministral-3-Reasoning-2512-AIO-GGUF/blob/main/Ministral-3-14B-Reasoning-2512-Q4_K_M.gguf) | | Ministral-3-14B-Reasoning-2512-Q5_K_M.gguf | Q5_K_M | 9.62 GB | [Download](https://huggingface.co/prithivMLmods/Ministral-3-Reasoning-2512-AIO-GGUF/blob/main/Ministral-3-14B-Reasoning-2512-Q5_K_M.gguf) | | Ministral-3-14B-Reasoning-2512-Q8_0.gguf | Q8_0 | 14.4 GB | [Download](https://huggingface.co/prithivMLmods/Ministral-3-Reasoning-2512-AIO-GGUF/blob/main/Ministral-3-14B-Reasoning-2512-Q8_0.gguf) | | Ministral-3-14B-Reasoning-2512-BF16-mmproj.gguf | BF16-mmproj | 879 MB | [Download](https://huggingface.co/prithivMLmods/Ministral-3-Reasoning-2512-AIO-GGUF/blob/main/Ministral-3-14B-Reasoning-2512-BF16-mmproj.gguf) | ## Ministral-3-8B-Reasoning-2512 [GGUF] | File Name | Quant Type | File Size | File Link | | - | - | - | - | | Ministral-3-8B-Reasoning-2512-BF16.gguf | BF16 | 17 GB | [Download](https://huggingface.co/prithivMLmods/Ministral-3-Reasoning-2512-AIO-GGUF/blob/main/Ministral-3-8B-Reasoning-2512-BF16.gguf) | | Ministral-3-8B-Reasoning-2512-Q4_K_M.gguf | Q4_K_M | 5.2 GB | [Download](https://huggingface.co/prithivMLmods/Ministral-3-Reasoning-2512-AIO-GGUF/blob/main/Ministral-3-8B-Reasoning-2512-Q4_K_M.gguf) | | Ministral-3-8B-Reasoning-2512-Q5_K_M.gguf | Q5_K_M | 6.06 GB | [Download](https://huggingface.co/prithivMLmods/Ministral-3-Reasoning-2512-AIO-GGUF/blob/main/Ministral-3-8B-Reasoning-2512-Q5_K_M.gguf) | | Ministral-3-8B-Reasoning-2512-Q8_0.gguf | Q8_0 | 9.03 GB | [Download](https://huggingface.co/prithivMLmods/Ministral-3-Reasoning-2512-AIO-GGUF/blob/main/Ministral-3-8B-Reasoning-2512-Q8_0.gguf) | | Ministral-3-8B-Reasoning-2512-BF16-mmproj.gguf | BF16-mmproj | 858 MB | [Download](https://huggingface.co/prithivMLmods/Ministral-3-Reasoning-2512-AIO-GGUF/blob/main/Ministral-3-8B-Reasoning-2512-BF16-mmproj.gguf) | ## Ministral-3-3B-Reasoning-2512 [GGUF] | File Name | Quant Type | File Size | File Link | | - | - | - | - | | Ministral-3-3B-Reasoning-2512-BF16.gguf | BF16 | 6.87 GB | [Download](https://huggingface.co/prithivMLmods/Ministral-3-Reasoning-2512-AIO-GGUF/blob/main/Ministral-3-3B-Reasoning-2512-BF16.gguf) | | Ministral-3-3B-Reasoning-2512-Q4_K_M.gguf | Q4_K_M | 2.15 GB | [Download](https://huggingface.co/prithivMLmods/Ministral-3-Reasoning-2512-AIO-GGUF/blob/main/Ministral-3-3B-Reasoning-2512-Q4_K_M.gguf) | | Ministral-3-3B-Reasoning-2512-Q5_K_M.gguf | Q5_K_M | 2.47 GB | [Download](https://huggingface.co/prithivMLmods/Ministral-3-Reasoning-2512-AIO-GGUF/blob/main/Ministral-3-3B-Reasoning-2512-Q5_K_M.gguf) | | Ministral-3-3B-Reasoning-2512-Q8_0.gguf | Q8_0 | 3.65 GB | [Download](https://huggingface.co/prithivMLmods/Ministral-3-Reasoning-2512-AIO-GGUF/blob/main/Ministral-3-3B-Reasoning-2512-Q8_0.gguf) | | Ministral-3-3B-Reasoning-2512-BF16-mmproj.gguf | BF16-mmproj | 842 MB | [Download](https://huggingface.co/prithivMLmods/Ministral-3-Reasoning-2512-AIO-GGUF/blob/main/Ministral-3-3B-Reasoning-2512-BF16-mmproj.gguf) | ## Quants Usage (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)