MI

SpermLLM S1 Ministral3 4B

MistralGGUF by SpermAIUpdated 2026-02-23
Download on Hugging Face
Parameters3.83B
Context256K
Layers26
Architecturemistral3
Smallest quant7.7 GB
Quick answer

SpermLLM S1 Ministral3 4B needs about 9.0 GB of memory at BF16 (a 7.7 GB file) with an 8K context window, so it fits on a 12 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 3.5 GB.

SpermLLM S1 Ministral3 4B is a 3.83B-parameter Mistral model in GGUF format, quantized by SpermAI. Its trained context length is 256K tokens. The repository has 1 quant file, from 7.7 GB (BF16) to 7.7 GB (BF16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
BF167.7 GB 9.0 GB
Too big Get file →

What GPU do you need for SpermLLM S1 Ministral3 4B?

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: the best quant that fits is BF16 (7.7 GB file, about 9.0 GB in use).

Which SpermLLM S1 Ministral3 4B quant should you choose?

BF16 (7.7 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
Parameters3.83B
Layers26
Trained context262,144 tokens
KV cache (fp16)104 KB per token

Source

Quantized bySpermAI
FamilyMistral
Licenseapache-2.0
Downloads (HF)44
Last updated2026-02-23

Frequently asked questions about SpermLLM S1 Ministral3 4B

How much VRAM does SpermLLM S1 Ministral3 4B need?

About 9.0 GB at BF16 with an 8K context window. That is the 7.7 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 SpermLLM S1 Ministral3 4B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 9.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of SpermLLM S1 Ministral3 4B GGUF?

It depends on the quant: BF16 is 7.7 GB.

What context length does SpermLLM S1 Ministral3 4B 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 SpermLLM S1 Ministral3 4B GGUF?

The files are on Hugging Face in the SpermAI/SpermLLM-S1-Ministral3-4B repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does SpermLLM S1 Ministral3 4B 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.

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

Similar models

Browse all →

More from SpermAI

All by SpermAI →

More Mistral models

All Mistral →

Other small models

All small models →