MI

Ministral 3 14B Instruct 2512

MistralGGUF by eaddarioUpdated 2026-02-01
Download on Hugging Face
Parameters13.5B
Context256K
Layers40
Architecturemistral3
Smallest quant0.0 GB
Quick answer

Ministral 3 14B Instruct 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 18 quants, from 0.0 GB to 27.0 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

Ministral 3 14B Instruct 2512 – 13.5B language model with vision and agentic capabilities

Ministral 3 14B Instruct 2512 is a 13.5B parameter model in the Mistral family. It supports a 256k context window, vision input, and native function calling. The model is released under Apache‑2.0 and can run on a range of hardware, including local edge devices.

Good at

  • Large context handling
  • Vision‑enabled instruction following
  • Agentic function calling

Limits

  • No native vision support in quantized builds
  • Requires 24GB VRAM in FP8 for full model
  • Large context window may exceed VRAM on low‑end GPUs

Best for

  • Private chat assistants
  • Local agentic workflows
  • Fine‑tuning for specialized tasks

Who it’s for. Developers and data scientists building private AI deployments that need advanced instruction following and vision support on edge hardware. The model is suitable for both commercial and non‑commercial use under the Apache‑2.0 license.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 1.9 GB
Fits Get file →
—3.0 GB 4.8 GB
Fits Get file →
IQ2_XXS3.4 GB 5.2 GB
Fits Get file →
IQ2_XS3.6 GB 5.4 GB
Fits Get file →
IQ2_S3.8 GB 5.6 GB
Fits Get file →
Q2_K4.2 GB 6.1 GB
Fits Get file →
IQ3_XXS5.1 GB 6.9 GB
Fits Get file →
Q3_K_S5.5 GB 7.3 GB
Tight Get file →
Q3_K5.9 GB 7.8 GB
Tight Get file →
Q3_K_L6.3 GB 8.2 GB
Too big Get file →
Q4_K_S7.2 GB 9.0 GB
Too big Get file →
Q4_K7.6 GB 9.4 GB
Too big Get file →
Q4_K_M8.2 GB 10.1 GB
Too big Get file →
Q5_K_S8.9 GB 10.7 GB
Too big Get file →
Q5_K9.3 GB 11.1 GB
Too big Get file →
Q6_K11.0 GB 12.8 GB
Too big Get file →
Q8_014.4 GB 16.2 GB
Too big Get file →
F1627.0 GB 28.9 GB
Too big Get file →

For 8GB VRAM use Q4_K_S (7.18 GB file, ~9 GB memory). For 12GB VRAM use Q5_K (9.29 GB file, ~11.1 GB memory). For 24GB VRAM use FP8 (unknown size) or Q8_0 (14.36 GB file, ~16.2 GB memory). Memory estimates are approximate.

What GPU do you need for Ministral 3 14B Instruct 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 1.9 GB in use).
  • 6 GB VRAM: the best quant that fits is IQ2_S (3.8 GB file, about 5.6 GB in use).
  • 8 GB VRAM: the best quant that fits is Q3_K (5.9 GB file, about 7.8 GB in use).
  • 12 GB VRAM: the best quant that fits is Q5_K (9.3 GB file, about 11.1 GB in use).
  • 16 GB VRAM: the best quant that fits is Q6_K (11.0 GB file, about 12.8 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 F16 (27.0 GB file, about 28.9 GB in use).

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

Q4_K_M is the usual starting point for Ministral 3 14B Instruct 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 byeaddario
FamilyMistral
Licenseapache-2.0
Downloads (HF)988
Last updated2026-02-01

Frequently asked questions about Ministral 3 14B Instruct 2512

How much VRAM does Ministral 3 14B Instruct 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 Instruct 2512 on an 8 GB GPU?

Yes, with Q3_K: the 5.9 GB file needs about 7.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

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

It depends on the quant: file is 0.0 GB, file is 3.0 GB, IQ2_XXS is 3.4 GB, IQ2_XS is 3.6 GB, IQ2_S is 3.8 GB, Q2_K is 4.2 GB and 12 more.

What context length does Ministral 3 14B Instruct 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 Instruct 2512 GGUF?

The files are on Hugging Face in the eaddario/Ministral-3-14B-Instruct-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 Instruct 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?

Use the Q4_K_S quantization; it requires about 9 GB VRAM at 8k context.

Does the model support vision in quantized versions?

Vision support is available only in the full FP8 model; quantized builds lack native vision capability.

What license applies to this model?

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

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

Similar models

Browse all →

More from eaddario

All by eaddario →

More Mistral models

All Mistral →

Other medium models

All medium models →