MI

Ministral 3 14B Reasoning 2512

MistralGGUF by bartowskiUpdated 2025-12-19
Download on Hugging Face
Parameters13.5B
Context256K
Layers40
Architecturemistral3
Smallest quant0.0 GB
Quick answer

Ministral 3 14B Reasoning 2512 needs about 10.1 GB of memory at Q4_K_M (a 8.2 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 26 quants, from 0.0 GB to 27.0 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

Ministral 3 14B Reasoning 2512 – a 13.5B model with vision and reasoning

Ministral 3 14B Reasoning 2512 is a 13.5B parameter model with a 0.4B vision encoder. It supports a 256k context window and is trained for complex reasoning tasks such as math, coding and STEM. The model is open‑source under Apache 2.0 and can run on a wide range of hardware.

Good at

  • Vision analysis and image insight
  • Complex multi‑step reasoning
  • Agentic function calling

Limits

  • Large context window requires high VRAM
  • No explicit language list provided
  • Requires 8k context for memory estimates

Best for

  • Local AI assistants in constrained environments
  • Advanced agentic use cases
  • Fine‑tuning for specialized tasks

Who it’s for. Developers and researchers who need a reasoning‑focused model with vision support that can be deployed locally. The model is suitable for private AI deployments and edge devices that can accommodate the required VRAM and RAM.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 1.8 GB
Fits Get file →
IQ2_S4.5 GB 6.4 GB
Fits Get file →
IQ2_M4.8 GB 6.7 GB
Fits Get file →
Q2_K5.2 GB 7.1 GB
Fits Get file →
IQ3_XXS5.4 GB 7.3 GB
Tight Get file →
IQ3_XS5.8 GB 7.7 GB
Tight Get file →
Q2_K_L5.9 GB 7.7 GB
Tight Get file →
Q3_K_S6.1 GB 7.9 GB
Tight Get file →
IQ3_M6.3 GB 8.1 GB
Too big Get file →
Q3_K_M6.7 GB 8.5 GB
Too big Get file →
Q3_K_L7.2 GB 9.1 GB
Too big Get file →
IQ4_XS7.4 GB 9.3 GB
Too big Get file →
Q3_K_XL7.8 GB 9.6 GB
Too big Get file →
IQ4_NL7.8 GB 9.6 GB
Too big Get file →
Q4_07.8 GB 9.6 GB
Too big Get file →
Q4_K_S7.8 GB 9.7 GB
Too big Get file →
Q4_K_M8.2 GB 10.1 GB
Too big Get file →
Q4_18.6 GB 10.4 GB
Too big Get file →
Q4_K_L8.7 GB 10.6 GB
Too big Get file →
Q5_K_S9.4 GB 11.2 GB
Too big Get file →
Q5_K_M9.6 GB 11.5 GB
Too big Get file →
Q5_K_L10.0 GB 11.9 GB
Too big Get file →
Q6_K11.1 GB 12.9 GB
Too big Get file →
Q6_K_L11.4 GB 13.3 GB
Too big Get file →
Q8_014.4 GB 16.2 GB
Too big Get file →
BF1627.0 GB 28.9 GB
Too big Get file →

For 8GB VRAM, use Q4_0 (file size 7.81 GB, memory 9.6 GB). For 12GB VRAM, Q4_K_M (8.24 GB, 10.1 GB) or Q5_K_S (9.38 GB, 11.2 GB) are suitable. For 16GB VRAM, Q6_K (11.09 GB, 12.9 GB) or Q6_K_L (11.41 GB, 13.3 GB) provide higher quality. Memory estimates are approximate.

What GPU do you need for Ministral 3 14B Reasoning 2512?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 1.8 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 1.8 GB in use).
  • 8 GB VRAM: the best quant that fits is Q3_K_S (6.1 GB file, about 7.9 GB in use).
  • 12 GB VRAM: the best quant that fits is Q5_K_L (10.0 GB file, about 11.9 GB in use).
  • 16 GB VRAM: the best quant that fits is Q6_K_L (11.4 GB file, about 13.3 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (14.4 GB file, about 16.2 GB in use).
  • 32 GB VRAM: the best quant that fits is BF16 (27.0 GB file, about 28.9 GB in use).

Which Ministral 3 14B Reasoning 2512 quant should you choose?

Q4_K_M is the usual starting point for Ministral 3 14B Reasoning 2512: it balances file size and quality well. Here it is a 8.2 GB file.

The Q8_0 file is 14.4 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturemistral3
Parameters13.5B
Layers40
Trained context262,144 tokens
KV cache (fp16)160 KB per token

Source

Quantized bybartowski
FamilyMistral
Licenseapache-2.0
Downloads (HF)2,579
Last updated2025-12-19

Frequently asked questions about Ministral 3 14B Reasoning 2512

How much VRAM does Ministral 3 14B Reasoning 2512 need?

About 10.1 GB at Q4_K_M with an 8K context window. That is the 8.2 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run Ministral 3 14B Reasoning 2512 on an 8 GB GPU?

Yes, with Q3_K_S: the 6.1 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Ministral 3 14B Reasoning 2512 GGUF?

It depends on the quant: file is 0.0 GB, IQ2_S is 4.5 GB, IQ2_M is 4.8 GB, Q2_K is 5.2 GB, IQ3_XXS is 5.4 GB, IQ3_XS is 5.8 GB and 20 more.

What context length does Ministral 3 14B Reasoning 2512 support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.3 GB at 8K and 5.4 GB at 32K.

Where can I download Ministral 3 14B Reasoning 2512 GGUF?

The files are on Hugging Face in the bartowski/mistralai_Ministral-3-14B-Reasoning-2512-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Ministral 3 14B Reasoning 2512 use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run this model on 8 GB VRAM?

Yes, the Q4_0 quantization requires about 9.6 GB of VRAM at 8k context, which is close to 8 GB but may need swapping or a smaller context.

Does this model support vision?

Yes, it includes a 0.4B vision encoder and can analyze images.

What license does it use?

The model is released under the Apache 2.0 license, allowing commercial and non‑commercial use.

Other GGUFs of Ministral-3-14B-Reasoning-2512

Similar models

Browse all →

More from bartowski

All by bartowski →

More Mistral models

All Mistral →

Other medium models

All medium models →