MJ

Mjollnir 3B iQ5 K S

MjollnirGGUF by IntelligentEstateUpdated 2025-03-06
Download on Hugging Face
Parameters3.09B
Context32K
Layers36
Architectureqwen2
Smallest quant2.2 GB
Quick answer

Mjollnir 3B iQ5 K S needs about 3.0 GB of memory at Q5_K_S (a 2.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 1.2 GB.

Mjollnir 3B iQ5 K S is a 3.09B-parameter Mjollnir model in GGUF format, quantized by IntelligentEstate. Its trained context length is 32K tokens. The repository has 1 quant file, from 2.2 GB (Q5_K_S) to 2.2 GB (Q5_K_S).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_S2.2 GB 3.0 GB
Fits Get file →

What GPU do you need for Mjollnir 3B iQ5 K S?

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 Q5_K_S (2.2 GB file, about 3.0 GB in use).

Which Mjollnir 3B iQ5 K S quant should you choose?

Q5_K_S (2.2 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.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen2
Parameters3.09B
Layers36
Trained context32,768 tokens
KV cache (fp16)36 KB per token

Source

Quantized byIntelligentEstate
FamilyMjollnir
Licensegpl
Downloads (HF)46
Last updated2025-03-06

Frequently asked questions about Mjollnir 3B iQ5 K S

How much VRAM does Mjollnir 3B iQ5 K S need?

About 3.0 GB at Q5_K_S with an 8K context window. That is the 2.2 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 Mjollnir 3B iQ5 K S on an 8 GB GPU?

Yes, with Q5_K_S: the 2.2 GB file needs about 3.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Mjollnir 3B iQ5 K S GGUF?

It depends on the quant: Q5_K_S is 2.2 GB.

What context length does Mjollnir 3B iQ5 K S support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.3 GB at 8K and 1.2 GB at 32K.

Where can I download Mjollnir 3B iQ5 K S GGUF?

The files are on Hugging Face in the IntelligentEstate/Mjollnir-3B-iQ5-K_S-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 Mjollnir 3B iQ5 K S use?

Hugging Face lists the license as gpl. 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 IntelligentEstate

All by IntelligentEstate →

Other tiny models

All tiny models →