TR

Translategemma 12b It

TranslategemmaGGUF by 42ailabUpdated 2026-07-26
Download on Hugging Face
Parameters11.8B
Context128K
Layers48
Architecturegemma3
Smallest quant7.3 GB
Quick answer

Translategemma 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.

Local multilingual translation model

Translategemma 12b It is a 11.8 billion‑parameter Gemma3 model quantized to Q4_K_M. It translates text between 55 languages entirely offline. The GGUF file is 7.3 GB and requires about 11 GB of memory at 8 k context.

Good at

  • Multilingual translation
  • Privacy‑first offline use
  • Balanced tier performance

Limits

  • No vision support
  • Requires 11 GB VRAM at 8 k context
  • No other task support

Best for

  • Local translation of documents
  • Privacy‑sensitive content conversion
  • Offline multilingual chat

Who it’s for. Users who need to translate text without sending data to the cloud. Ideal for developers building private translation tools or individuals handling sensitive documents.

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 of VRAM for 8 k context. If you have less than 11 GB, the model will not run. No other quants are provided.

What GPU do you need for Translategemma 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 Translategemma 12b It quant should you choose?

Q4_K_M is the usual starting point for Translategemma 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 by42ailab
Licensegemma
Downloads (HF)169
Last updated2026-07-26

Frequently asked questions about Translategemma 12b It

How much VRAM does Translategemma 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 Translategemma 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 Translategemma 12b It GGUF?

It depends on the quant: Q4_K_M is 7.3 GB.

What context length does Translategemma 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 Translategemma 12b It GGUF?

The files are on Hugging Face in the 42ailab/TranslateGemma-12B-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 Translategemma 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 this model on 8 GB VRAM?

No, the model requires about 11 GB of VRAM at 8 k context.

Is there a smaller quant available?

Only the Q4_K_M quant is provided; no other sizes exist.

Is the model free to use?

Yes, it is released under the Gemma Terms of Use and can be used without cost.

Other GGUFs of translategemma-12b-it

Similar models

Browse all →

More from 42ailab

All by 42ailab →

More Translategemma models

All Translategemma →

Other medium models

All medium models →