GE

MagicSpellGemma

GemmaGGUF by NormanHsiaoUpdated 2025-10-20
Download on Hugging Face
Parameters268M
Context32K
Layers18
Architecturegemma3
Smallest quant0.5 GB
Quick answer

MagicSpellGemma needs about 1.2 GB of memory at F16 (a 0.5 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 0.6 GB.

MagicSpellGemma is a 268M-parameter Gemma model in GGUF format, quantized by NormanHsiao. Its trained context length is 32K tokens. The repository has 1 quant file, from 0.5 GB (F16) to 0.5 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F160.5 GB 1.2 GB
Fits Get file →

What GPU do you need for MagicSpellGemma?

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 F16 (0.5 GB file, about 1.2 GB in use).

Which MagicSpellGemma quant should you choose?

F16 (0.5 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

Architecturegemma3
Parameters268M
Layers18
Trained context32,768 tokens
KV cache (fp16)18 KB per token

Source

Quantized byNormanHsiao
FamilyGemma
Downloads (HF)7
Last updated2025-10-20

Frequently asked questions about MagicSpellGemma

How much VRAM does MagicSpellGemma need?

About 1.2 GB at F16 with an 8K context window. That is the 0.5 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 MagicSpellGemma on an 8 GB GPU?

Yes, with F16: the 0.5 GB file needs about 1.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of MagicSpellGemma GGUF?

It depends on the quant: F16 is 0.5 GB.

What context length does MagicSpellGemma support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.6 GB at 32K.

Where can I download MagicSpellGemma GGUF?

The files are on Hugging Face in the NormanHsiao/MagicSpellGemma-268M-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Other GGUFs of gemma-3-270m-it

Similar models

Browse all →

More Gemma models

All Gemma →

Other tiny models

All tiny models →