MI

mistralai_Ministral 3 8B Instruct 2512 BF16

MistralGGUF by lmstudio-communityUpdated 2025-12-02
Download on Hugging Face
Parameters8.49B
Context256K
Layers34
Architecturemistral3
Smallest quant5.2 GB
Quick answer

mistralai_Ministral 3 8B Instruct 2512 BF16 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 3 quants, from 5.2 GB (Q4_K_M) to 9.0 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.6 GB.

Mistral 3 8B Instruct with vision, 256k context, Apache 2.0 licensed

Mistral 3 8B Instruct 2512 BF16 is a balanced 8B language model with a 0.4B vision encoder. It supports a 256k token context window and is fine‑tuned for instruction tasks. The model is edge‑optimized and can run locally on modest hardware.

Good at

  • Instruction following
  • Vision analysis
  • Large context handling

Limits

  • Vision support only, no audio
  • Requires 8k context for memory estimates
  • Apache 2.0 license restricts certain uses

Best for

  • Chat in constrained environments
  • Local AI assistant
  • Image/document description

Who it’s for. Developers building local or embedded AI assistants that need instruction compliance and vision. Ideal for teams requiring a small, efficient model with a large context window.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M5.2 GB 6.8 GB
Fits Get file →
Q6_K7.0 GB 8.6 GB
Too big Get file →
Q8_09.0 GB 10.7 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (5.2 GB, ~6.8 GB RAM). For 12 GB VRAM, Q6_K (6.97 GB, ~8.6 GB RAM). Q8_0 needs ~10.7 GB RAM and 9.03 GB file size.

What GPU do you need for mistralai_Ministral 3 8B Instruct 2512 BF16?

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: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: the best quant that fits is Q4_K_M (5.2 GB file, about 6.8 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (9.0 GB file, about 10.7 GB in use).

Which mistralai_Ministral 3 8B Instruct 2512 BF16 quant should you choose?

Q4_K_M is the usual starting point for mistralai_Ministral 3 8B Instruct 2512 BF16: 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.

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 bylmstudio-community
FamilyMistral
Licenseapache-2.0
Downloads (HF)4,638
Last updated2025-12-02

Frequently asked questions about mistralai_Ministral 3 8B Instruct 2512 BF16

How much VRAM does mistralai_Ministral 3 8B Instruct 2512 BF16 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 mistralai_Ministral 3 8B Instruct 2512 BF16 on an 8 GB GPU?

Yes, with Q4_K_M: the 5.2 GB file needs about 6.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of mistralai_Ministral 3 8B Instruct 2512 BF16 GGUF?

It depends on the quant: Q4_K_M is 5.2 GB, Q6_K is 7.0 GB, Q8_0 is 9.0 GB.

What context length does mistralai_Ministral 3 8B Instruct 2512 BF16 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 mistralai_Ministral 3 8B Instruct 2512 BF16 GGUF?

The files are on Hugging Face in the lmstudio-community/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 mistralai_Ministral 3 8B Instruct 2512 BF16 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_K_M quantization requires about 6.8 GB of RAM at 8k context, fitting within 8 GB VRAM.

Does it support image input?

Yes, it includes a 0.4B vision encoder for image analysis.

What license applies?

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

Other GGUFs of Ministral-3-8B-Instruct-2512-BF16

Similar models

Browse all →

More from lmstudio-community

All by lmstudio-community →

More Mistral models

All Mistral →

Other small models

All small models →