MI

ministral 3 3b reasoning 2512

MistralGGUF by nile-academyUpdated 2026-10-20
Download on Hugging Face
Parameters3.43B
Context256K
Layers26
Architecturemistral3
Smallest quant2.1 GB
Quick answer

ministral 3 3b reasoning 2512 needs about 3.5 GB of memory at Q4_K_M (a 2.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 4 quants, from 2.1 GB (Q4_K_M) to 6.9 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.5 GB.

Ministral 3 3B Reasoning 2512 – a compact, vision‑enabled LLM for edge deployment

Ministral 3 3B Reasoning 2512 is a 3.43 billion‑parameter model with a 256k context window. It includes a 0.4B vision encoder and is optimized for reasoning, coding, and STEM tasks. The model runs on a wide range of hardware, fitting in 16GB VRAM in BF16 and less than 8GB when quantized.

Good at

  • Reasoning and multi‑step problem solving
  • Vision‑enabled image analysis
  • Agentic function calling with JSON output

Limits

  • No dedicated vision support in quantized files
  • Requires 8k context for memory estimates
  • Apache‑2.0 license limits commercial redistribution of weights

Best for

  • Real‑time image captioning on edge devices
  • Low‑resource text classification
  • On‑device translation with minimal VRAM

Who it’s for. Developers building lightweight, real‑time applications on edge or low‑resource devices. The model is suitable for those needing reasoning, vision, and multilingual capabilities without large GPU requirements.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M2.1 GB 3.5 GB
Fits Get file →
Q5_K_M2.5 GB 3.8 GB
Fits Get file →
Q8_03.7 GB 5.0 GB
Fits Get file →
BF166.9 GB 8.2 GB
Too big Get file →

For 8GB VRAM, use Q4_K_M (2.15 GB, ~3.5 GB memory at 8k context) or Q5_K_M (2.47 GB, ~3.8 GB). For 16GB VRAM, BF16 (6.87 GB, ~8.2 GB) offers higher precision. Memory estimates are approximate.

What GPU do you need for ministral 3 3b 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 Q5_K_M (2.5 GB file, about 3.8 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (3.7 GB file, about 5.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (3.7 GB file, about 5.0 GB in use).
  • 12 GB VRAM: the best quant that fits is BF16 (6.9 GB file, about 8.2 GB in use).

Which ministral 3 3b reasoning 2512 quant should you choose?

Q4_K_M is the usual starting point for ministral 3 3b reasoning 2512: it balances file size and quality well. Here it is a 2.1 GB file.

The Q8_0 file is 3.7 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.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturemistral3
Parameters3.43B
Layers26
Trained context262,144 tokens
KV cache (fp16)104 KB per token

Source

Quantized bynile-academy
FamilyMistral
Licenseapache-2.0
Downloads (HF)681
Last updated2026-10-20

Frequently asked questions about ministral 3 3b reasoning 2512

How much VRAM does ministral 3 3b reasoning 2512 need?

About 3.5 GB at Q4_K_M with an 8K context window. That is the 2.1 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 3b reasoning 2512 on an 8 GB GPU?

Yes, with Q8_0: the 3.7 GB file needs about 5.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of ministral 3 3b reasoning 2512 GGUF?

It depends on the quant: Q4_K_M is 2.1 GB, Q5_K_M is 2.5 GB, Q8_0 is 3.7 GB, BF16 is 6.9 GB.

What context length does ministral 3 3b 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 0.9 GB at 8K and 3.5 GB at 32K.

Where can I download ministral 3 3b reasoning 2512 GGUF?

The files are on Hugging Face in the nile-academy/ministral-3-3b-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 3b 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, using Q4_K_M or Q5_K_M quantizations keeps VRAM usage below 8 GB, though memory estimates are approximate.

Does the model support vision tasks after quantization?

The quantized files do not include dedicated vision support; the original model has a 0.4B vision encoder.

What license applies to the weights?

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

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

Similar models

Browse all →

More from nile-academy

All by nile-academy →

More Mistral models

All Mistral →

Other tiny models

All tiny models →