TR

translategemma 27b it MXFP4 MOE

TranslategemmaGGUF by yeoj34760Updated 2026-01-22
Download on Hugging Face
Parameters27B
Context128K
Layers62
Architecturegemma3
Smallest quant28.7 GB
Quick answer

translategemma 27b it MXFP4 MOE needs about 33.4 GB of memory at MXFP4_MOE (a 28.7 GB file) with an 8K context window, so it fits on a 48 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 16.6 GB.

translategemma 27b it MXFP4 MOE is a 27B-parameter Translategemma model in GGUF format, quantized by yeoj34760. Its trained context length is 128K tokens. The repository has 1 quant file, from 28.7 GB (MXFP4_MOE) to 28.7 GB (MXFP4_MOE).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
MXFP4_MOE28.7 GB 33.4 GB
Too big Get file →

What GPU do you need for translategemma 27b it MXFP4 MOE?

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: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: no quant fits at an 8K context.
  • 32 GB VRAM: no quant fits at an 8K context.
  • 48 GB VRAM: the best quant that fits is MXFP4_MOE (28.7 GB file, about 33.4 GB in use).

Which translategemma 27b it MXFP4 MOE quant should you choose?

MXFP4_MOE (28.7 GB) is the middle option in this repository. Lower bit counts mean smaller files and more quality loss.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegemma3
Parameters27B
Layers62
Trained context131,072 tokens
KV cache (fp16)496 KB per token

Source

Quantized byyeoj34760
Licensegemma
Downloads (HF)49
Last updated2026-01-22

Frequently asked questions about translategemma 27b it MXFP4 MOE

How much VRAM does translategemma 27b it MXFP4 MOE need?

About 33.4 GB at MXFP4_MOE with an 8K context window. That is the 28.7 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 27b it MXFP4 MOE on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 33.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of translategemma 27b it MXFP4 MOE GGUF?

It depends on the quant: MXFP4_MOE is 28.7 GB.

What context length does translategemma 27b it MXFP4 MOE support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 4.2 GB at 8K and 16.6 GB at 32K.

Where can I download translategemma 27b it MXFP4 MOE GGUF?

The files are on Hugging Face in the yeoj34760/translategemma-27b-it-MXFP4_MOE-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 27b it MXFP4 MOE 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.

Other GGUFs of translategemma-27b-it

Similar models

Browse all →

More from yeoj34760

All by yeoj34760 →

More Translategemma models

All Translategemma →

Other medium models

All medium models →