MI

Ministral-3-8B-Instruct-2512

MistralGGUF by unslothUpdated 2025-12-04
Download on Hugging Face
Parameters8.49B
Context256K
Layers34
Architecturemistral3
Smallest quant2.3 GB
Quick answer

Ministral-3-8B-Instruct-2512 needs about 6.8 GB of memory at Q4_K_M (a 5.2 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 26 quants, from 2.3 GB (IQ1_S) to 17.0 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.6 GB.

Ministral‑3‑8B‑Instruct‑2512: 8B language model with vision, edge‑optimized.

Ministral‑3‑8B‑Instruct‑2512 is an 8.4B language model with a 0.4B vision encoder. It supports a 256k context window and is fine‑tuned for instruction tasks. The model is released under Apache 2.0 and can run locally on modest hardware.

Good at

  • Vision‑enabled text generation
  • Multilingual instruction following
  • Agentic function calling

Limits

  • Large context requires high VRAM
  • No native vision support in older quantizations
  • Requires 8‑bit or higher for full precision

Best for

  • Chat interfaces in constrained environments
  • Local AI assistants
  • Image/document description

Who it’s for. Developers building local or embedded AI assistants that need vision and multilingual support. The model is suitable for edge deployment and can be run on GPUs with 12 GB VRAM in FP8 or less with quantization.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S2.3 GB 3.9 GB
Fits Get file →
IQ1_M2.4 GB 4.1 GB
Fits Get file →
IQ2_XXS2.6 GB 4.3 GB
Fits Get file →
IQ2_M3.2 GB 4.8 GB
Fits Get file →
Q2_K3.4 GB 5.0 GB
Fits Get file →
Q2_K_L3.5 GB 5.1 GB
Fits Get file →
IQ3_XXS3.5 GB 5.1 GB
Fits Get file →
Q2_K_XL3.6 GB 5.2 GB
Fits Get file →
Q3_K_S3.9 GB 5.5 GB
Fits Get file →
Q3_K_M4.2 GB 5.9 GB
Fits Get file →
Q3_K_XL4.4 GB 6.1 GB
Fits Get file →
IQ4_XS4.7 GB 6.4 GB
Fits Get file →
Q4_04.9 GB 6.6 GB
Fits Get file →
IQ4_NL4.9 GB 6.6 GB
Fits Get file →
Q4_K_S5.0 GB 6.6 GB
Fits Get file →
Q4_K_M5.2 GB 6.8 GB
Fits Get file →
Q4_K_XL5.3 GB 6.9 GB
Fits Get file →
Q4_15.4 GB 7.1 GB
Fits Get file →
Q5_K_S5.9 GB 7.6 GB
Tight Get file →
Q5_K_M6.1 GB 7.7 GB
Tight Get file →
Q5_K_XL6.1 GB 7.7 GB
Tight Get file →
Q6_K7.0 GB 8.6 GB
Too big Get file →
Q6_K_XL7.7 GB 9.4 GB
Too big Get file →
Q8_09.0 GB 10.7 GB
Too big Get file →
Q8_K_XL11.1 GB 12.7 GB
Too big Get file →
BF1617.0 GB 18.6 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (≈6.8 GB memory at 8k context). With 12 GB VRAM, Q4_K_XL (≈6.9 GB) or Q5_K_S (≈7.6 GB) are suitable. For 16 GB VRAM, Q5_K_M (≈7.7 GB) or Q6_K (≈8.6 GB) provide higher precision. Memory estimates are approximate.

What GPU do you need for Ministral-3-8B-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 IQ1_S (2.3 GB file, about 3.9 GB in use).
  • 6 GB VRAM: the best quant that fits is Q3_K_M (4.2 GB file, about 5.9 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_K_XL (6.1 GB file, about 7.7 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (9.0 GB file, about 10.7 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_K_XL (11.1 GB file, about 12.7 GB in use).
  • 24 GB VRAM: the best quant that fits is BF16 (17.0 GB file, about 18.6 GB in use).

Which Ministral-3-8B-Instruct-2512 quant should you choose?

Q4_K_M is the usual starting point for Ministral-3-8B-Instruct-2512: it balances file size and quality well. Here it is a 5.2 GB file.

The Q8_0 file is 9.0 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 IQ1_S at 2.3 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturemistral3
Parameters8.49B
Layers34
Trained context262,144 tokens
KV cache (fp16)136 KB per token

Source

Quantized byunsloth
FamilyMistral
Licenseapache-2.0
Downloads (HF)19,457
Last updated2025-12-04

Frequently asked questions about Ministral-3-8B-Instruct-2512

How much VRAM does Ministral-3-8B-Instruct-2512 need?

About 6.8 GB at Q4_K_M with an 8K context window. That is the 5.2 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-3-8B-Instruct-2512 on an 8 GB GPU?

Yes, with Q5_K_XL: the 6.1 GB file needs about 7.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Ministral-3-8B-Instruct-2512 GGUF?

It depends on the quant: IQ1_S is 2.3 GB, IQ1_M is 2.4 GB, IQ2_XXS is 2.6 GB, IQ2_M is 3.2 GB, Q2_K is 3.4 GB, Q2_K_L is 3.5 GB and 20 more.

What context length does Ministral-3-8B-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 1.1 GB at 8K and 4.6 GB at 32K.

Where can I download Ministral-3-8B-Instruct-2512 GGUF?

The files are on Hugging Face in the unsloth/Ministral-3-8B-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-3-8B-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?

Yes, using Q4_K_M or Q4_K_S quantizations will fit within 8 GB VRAM with about 6.8–6.6 GB memory usage at 8k context.

Does the model support vision tasks?

Yes, it includes a 0.4B vision encoder and can analyze images in addition to text.

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-3-8B-Instruct-2512

Similar models

Browse all →

More from unsloth

All by unsloth →

More Mistral models

All Mistral →

Other small models

All small models →