GE

gemma3 4b BiliFilter v2

GemmaGGUF by dddngUpdated 2025-05-10
Download on Hugging Face
Parameters3.88B
Context128K
Layers34
Architecturegemma3
Smallest quant2.5 GB
Quick answer

gemma3 4b BiliFilter v2 needs about 4.1 GB of memory at its main file (a 2.5 GB file) with an 8K context window, so it fits on a 6 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 4.6 GB.

gemma3 4b BiliFilter v2 is a 3.88B-parameter Gemma model in GGUF format, quantized by dddng. Its trained context length is 128K tokens. The repository has 1 quant file, from 2.5 GB to 2.5 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—2.5 GB 4.1 GB
Fits Get file →

What GPU do you need for gemma3 4b BiliFilter v2?

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: the best quant that fits is the main file (2.5 GB file, about 4.1 GB in use).

Specifications

Architecture from the GGUF header

Architecturegemma3
Parameters3.88B
Layers34
Trained context131,072 tokens
KV cache (fp16)136 KB per token

Source

Quantized bydddng
FamilyGemma
Downloads (HF)4
Last updated2025-05-10

Frequently asked questions about gemma3 4b BiliFilter v2

How much VRAM does gemma3 4b BiliFilter v2 need?

About 4.1 GB at its main file with an 8K context window. That is the 2.5 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 4b BiliFilter v2 on an 8 GB GPU?

Yes, with the smaller files: the 2.5 GB file needs about 4.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of gemma3 4b BiliFilter v2 GGUF?

It depends on the quant: file is 2.5 GB.

What context length does gemma3 4b BiliFilter v2 support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.6 GB at 32K.

Where can I download gemma3 4b BiliFilter v2 GGUF?

The files are on Hugging Face in the dddng/gemma3_4b_BiliFilter_v2 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 dddng

All by dddng →

More Gemma models

All Gemma →

Other small models

All small models →