GE

gemma3 12b iq1s

GemmaGGUF by JohancolUpdated 2025-05-27
Download on Hugging Face
Parameters11.8B
Context128K
Layers48
Architecturegemma3
Smallest quant2.9 GB
Quick answer

gemma3 12b iq1s needs about 6.7 GB of memory at IQ1_S (a 2.9 GB file) with an 8K context window, so it fits on a 8 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 12.9 GB.

gemma3 12b iq1s is a 11.8B-parameter Gemma model in GGUF format, quantized by Johancol. Its trained context length is 128K tokens. The repository has 1 quant file, from 2.9 GB (IQ1_S) to 2.9 GB (IQ1_S).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S2.9 GB 6.7 GB
Fits Get file →

What GPU do you need for gemma3 12b iq1s?

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: the best quant that fits is IQ1_S (2.9 GB file, about 6.7 GB in use).

Which gemma3 12b iq1s quant should you choose?

IQ1_S (2.9 GB) is the middle option in this repository. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegemma3
Parameters11.8B
Layers48
Trained context131,072 tokens
KV cache (fp16)384 KB per token

Source

Quantized byJohancol
FamilyGemma
Licensegemma
Downloads (HF)17
Last updated2025-05-27

Frequently asked questions about gemma3 12b iq1s

How much VRAM does gemma3 12b iq1s need?

About 6.7 GB at IQ1_S with an 8K context window. That is the 2.9 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 gemma3 12b iq1s on an 8 GB GPU?

Yes, with IQ1_S: the 2.9 GB file needs about 6.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of gemma3 12b iq1s GGUF?

It depends on the quant: IQ1_S is 2.9 GB.

What context length does gemma3 12b iq1s support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 3.2 GB at 8K and 12.9 GB at 32K.

Where can I download gemma3 12b iq1s GGUF?

The files are on Hugging Face in the Johancol/gemma3-12b-iq1s repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does gemma3 12b iq1s use?

Hugging Face lists the license as gemma. 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 Johancol

All by Johancol →

More Gemma models

All Gemma →

Other medium models

All medium models →