MI

Ministral3BHeretic

MistralGGUF by salamanderDixonUpdated 2026-09-12
Download on Hugging Face
Parameters8.49B
Context256K
Layers34
Architecturemistral3
Smallest quant17.0 GB
Quick answer

Ministral3BHeretic needs about 18.6 GB of memory at BF16 (a 17.0 GB file) with an 8K context window, so it fits on a 24 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 4.6 GB.

Ministral3BHeretic is a 8.49B-parameter Mistral model in GGUF format, quantized by salamanderDixon. Its trained context length is 256K tokens. The repository has 1 quant file, from 17.0 GB (BF16) to 17.0 GB (BF16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
BF1617.0 GB 18.6 GB
Too big Get file →

What GPU do you need for Ministral3BHeretic?

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: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: the best quant that fits is BF16 (17.0 GB file, about 18.6 GB in use).

Which Ministral3BHeretic quant should you choose?

BF16 (17.0 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

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 bysalamanderDixon
FamilyMistral
Licenseapache-2.0
Downloads (HF)10
Last updated2026-09-12

Frequently asked questions about Ministral3BHeretic

How much VRAM does Ministral3BHeretic need?

About 18.6 GB at BF16 with an 8K context window. That is the 17.0 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 Ministral3BHeretic on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 18.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Ministral3BHeretic GGUF?

It depends on the quant: BF16 is 17.0 GB.

What context length does Ministral3BHeretic 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 Ministral3BHeretic GGUF?

The files are on Hugging Face in the salamanderDixon/Ministral3BHeretic-bf16.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 Ministral3BHeretic 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.

Similar models

Browse all →

More from salamanderDixon

All by salamanderDixon →

More Mistral models

All Mistral →

Other small models

All small models →