MI

Ministral 3 8B Instruct 2512

MistralGGUF by EnlistedGhostUpdated 2026-09-06
Download on Hugging Face
Parameters8.49B
Context256K
Layers34
Architecturemistral3
Smallest quant3.9 GB
Quick answer

Ministral 3 8B Instruct 2512 needs about 8.3 GB of memory at Q5_K_XL (a 6.6 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 7 quants, from 3.9 GB (Q2_K_L) to 17.0 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.6 GB.

Ministral 3 8B Instruct 2512 – a vision‑capable, edge‑optimized LLM

Ministral 3 8B Instruct 2512 is a 8.49 B parameter model with a 0.4 B vision encoder. It supports a 262144‑token context window and is fine‑tuned for instruction tasks. The model is licensed under Apache 2.0 and is designed for local or embedded deployment.

Good at

  • Vision analysis
  • Instruction following
  • Agentic function calling

Limits

  • No dedicated vision support in llama.cpp
  • Large context requires 256k tokens
  • Requires 12 GB+ VRAM for unquantized BF16

Best for

  • Local chat assistants
  • Multilingual instruction handling
  • Embedded vision applications

Who it’s for. Developers building local chatbots that need vision and instruction capabilities on modest hardware. The model is suitable for edge devices and small servers that can run GGUF files with llama.cpp.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K_L3.9 GB 5.5 GB
Fits Get file →
Q3_K_XL4.5 GB 6.1 GB
Fits Get file →
Q4_K_XL5.6 GB 7.2 GB
Tight Get file →
Q5_K_XL6.6 GB 8.3 GB
Too big Get file →
Q6_K_L8.3 GB 10.0 GB
Too big Get file →
Q8_011.7 GB 13.3 GB
Too big Get file →
F1617.0 GB 18.6 GB
Too big Get file →

For 8 GB VRAM use Q2_K_L (file size 3.88 GB, memory 5.5 GB). For 12 GB VRAM use Q3_K_XL (file size 4.47 GB, memory 6.1 GB). For 16 GB VRAM use Q4_K_XL (file size 5.6 GB, memory 7.2 GB).

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: no quant fits at an 8K context.
  • 6 GB VRAM: the best quant that fits is Q2_K_L (3.9 GB file, about 5.5 GB in use).
  • 8 GB VRAM: the best quant that fits is Q4_K_XL (5.6 GB file, about 7.2 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K_L (8.3 GB file, about 10.0 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (11.7 GB file, about 13.3 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (17.0 GB file, about 18.6 GB in use).

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

Q5_K_XL (6.6 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

If memory is tight, the smallest file is Q2_K_L at 3.9 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 byEnlistedGhost
FamilyMistral
Licenseapache-2.0
Downloads (HF)820
Last updated2026-09-06

Frequently asked questions about Ministral 3 8B Instruct 2512

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

About 8.3 GB at Q5_K_XL with an 8K context window. That is the 6.6 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 Q4_K_XL: the 5.6 GB file needs about 7.2 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: Q2_K_L is 3.9 GB, Q3_K_XL is 4.5 GB, Q4_K_XL is 5.6 GB, Q5_K_XL is 6.6 GB, Q6_K_L is 8.3 GB, Q8_0 is 11.7 GB and 1 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 EnlistedGhost/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, the Q2_K_L quantized file requires about 5.5 GB of VRAM at 8k context, fitting within an 8 GB budget.

Does the model support vision tasks in llama.cpp?

The model includes a vision encoder, but llama.cpp currently does not support vision; only text inference is available.

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-BF16

Similar models

Browse all →

More from EnlistedGhost

All by EnlistedGhost →

More Mistral models

All Mistral →

Other small models

All small models →