GE

Gemma 3 12b It

GemmaGGUF by nocturne23Updated 2025-03-13
Download on Hugging Face
Parameters11.8B
Context128K
Layers48
Architecturegemma3
Smallest quant7.3 GB
Quick answer

Gemma 3 12b It needs about 11.0 GB of memory at Q4_K_M (a 7.3 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 12.9 GB.

Gemma 3 12b It in GGUF format

Gemma 3 12b It is a 11.8 billion parameter language model converted to GGUF. It supports vision tasks and can be run with llama.cpp. The GGUF file is 7.3 GB and requires about 11 GB of VRAM at 8 k context.

Good at

  • Vision and text tasks
  • Large context support
  • Low memory footprint

Limits

  • No explicit vision API support
  • Requires 8 k context for full memory estimate
  • License is gemma

Best for

  • Vision‑enabled chatbots
  • Document summarization with image context
  • Multimodal data analysis

Who it’s for. Developers needing a compact vision‑capable model for local inference. Suitable for projects that can run llama.cpp and have at least 11 GB VRAM.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M7.3 GB 11.0 GB
Too big Get file →

The only available quant is Q4_K_M, 7.3 GB. It needs roughly 11 GB VRAM at 8 k context. For 8 GB VRAM, a higher quant would be required, but none are available in this release.

What GPU do you need for Gemma 3 12b It?

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 Q4_K_M (7.3 GB file, about 11.0 GB in use).

Which Gemma 3 12b It quant should you choose?

Q4_K_M is the usual starting point for Gemma 3 12b It: it balances file size and quality well. Here it is a 7.3 GB file.

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 bynocturne23
FamilyGemma
Licensegemma
Downloads (HF)613
Last updated2025-03-13

Frequently asked questions about Gemma 3 12b It

How much VRAM does Gemma 3 12b It need?

About 11.0 GB at Q4_K_M with an 8K context window. That is the 7.3 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 Gemma 3 12b It on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 11.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Gemma 3 12b It GGUF?

It depends on the quant: Q4_K_M is 7.3 GB.

What context length does Gemma 3 12b It 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 Gemma 3 12b It GGUF?

The files are on Hugging Face in the nocturne23/gemma-3-12b-it-Q4_K_M-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 Gemma 3 12b It 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.

Can I run Gemma 3 12b It on 8 GB VRAM?

No, the Q4_K_M quant requires about 11 GB VRAM at 8 k context. 8 GB VRAM is insufficient.

Does this model support vision?

Yes, it has detected vision abilities but no dedicated vision API is provided.

What is the context length?

The model was trained with 131072 tokens and supports that context length.

Other GGUFs of gemma-3-12b-it

Similar models

Browse all →

More from nocturne23

All by nocturne23 →

More Gemma models

All Gemma →

Other medium models

All medium models →