GE

gemma fft 2k e2

GemmaGGUF by Ful3Updated 2026-01-20
Download on Hugging Face
Parameters28.4B
Context128K
Layers62
Architecturegemma3
Smallest quant23.3 GB
Quick answer

gemma fft 2k e2 needs about 34.9 GB of memory at Q8_0 (a 30.2 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 3 quants, from 23.3 GB (Q6_K) to 56.8 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 16.6 GB.

gemma fft 2k e2 is a 28.4B-parameter Gemma model in GGUF format, quantized by Ful3. Its trained context length is 128K tokens. The repository has 3 quant files, from 23.3 GB (Q6_K) to 56.8 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q6_K23.3 GB 28.0 GB
Too big Get file →
Q8_030.2 GB 34.9 GB
Too big Get file →
F1656.8 GB 61.5 GB
Too big Get file →

What GPU do you need for gemma fft 2k e2?

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: the best quant that fits is Q6_K (23.3 GB file, about 28.0 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (30.2 GB file, about 34.9 GB in use).

Which gemma fft 2k e2 quant should you choose?

Q8_0 (30.2 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

If memory is tight, the smallest file is Q6_K at 23.3 GB, with the quality trade-offs that come with fewer bits. Very close to the original quality for most uses, at a clearly larger size than 4-bit.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegemma3
Parameters28.4B
Layers62
Trained context131,072 tokens
KV cache (fp16)496 KB per token

Source

Quantized byFul3
FamilyGemma
Downloads (HF)128
Last updated2026-01-20

Frequently asked questions about gemma fft 2k e2

How much VRAM does gemma fft 2k e2 need?

About 34.9 GB at Q8_0 with an 8K context window. That is the 30.2 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 fft 2k e2 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 28.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of gemma fft 2k e2 GGUF?

It depends on the quant: Q6_K is 23.3 GB, Q8_0 is 30.2 GB, F16 is 56.8 GB.

What context length does gemma fft 2k e2 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 gemma fft 2k e2 GGUF?

The files are on Hugging Face in the Ful3/gemma-fft-2k-e2 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More from Ful3

All by Ful3 →

More Gemma models

All Gemma →

Other medium models

All medium models →