GE

magnus supernova

GemmaGGUF by heavylildudeUpdated 2025-10-20
Download on Hugging Face
Parameters3.88B
Context128K
Layers—
Architecturegemma3
Smallest quant3.3 GB
Quick answer

magnus supernova needs about 4.2 GB of memory at Q4_K_M (a 3.3 GB file) with an 8K context window, so it fits on a 6 GB GPU.

magnus supernova is a 3.88B-parameter Gemma model in GGUF format, quantized by heavylildude. Its trained context length is 128K tokens. The repository has 1 quant file, from 3.3 GB (Q4_K_M) to 3.3 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M3.3 GB 4.2 GB
Fits Get file →

What GPU do you need for magnus supernova?

These figures add the file size, an fp16 KV cache at an 8K context window 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 Q4_K_M (3.3 GB file, about 4.2 GB in use).

Which magnus supernova quant should you choose?

Q4_K_M is the usual starting point for magnus supernova: it balances file size and quality well. Here it is a 3.3 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegemma3
Parameters3.88B
Trained context131,072 tokens

Source

Quantized byheavylildude
FamilyGemma
Licenseapache-2.0
Downloads (HF)0
Last updated2025-10-20

Frequently asked questions about magnus supernova

How much VRAM does magnus supernova need?

About 4.2 GB at Q4_K_M with an 8K context window. That is the 3.3 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 magnus supernova on an 8 GB GPU?

Yes, with Q4_K_M: the 3.3 GB file needs about 4.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of magnus supernova GGUF?

It depends on the quant: Q4_K_M is 3.3 GB.

What context length does magnus supernova support?

The GGUF header lists a trained context length of 131,072 tokens (128K).

Where can I download magnus supernova GGUF?

The files are on Hugging Face in the heavylildude/magnus-supernova repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does magnus supernova 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 gemma-3-4b-it

Similar models

Browse all →

More from heavylildude

All by heavylildude →

More Gemma models

All Gemma →

Other small models

All small models →