GE

gemma 3N finetune

GemmaGGUF by samanta-scratchUpdated 2025-11-07
Download on Hugging Face
Parameters6.87B
Context32K
Layers35
Architecturegemma3n
Smallest quant13.7 GB
Quick answer

gemma 3N finetune needs about 14.8 GB of memory at F16 (a 13.7 GB file) with an 8K context window, so it fits on a 16 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 2.3 GB.

gemma 3N finetune is a 6.87B-parameter Gemma model in GGUF format, quantized by samanta-scratch. Its trained context length is 32K tokens. The repository has 1 quant file, from 13.7 GB (F16) to 13.7 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F1613.7 GB 14.8 GB
Too big Get file →

What GPU do you need for gemma 3N finetune?

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: the best quant that fits is F16 (13.7 GB file, about 14.8 GB in use).

Which gemma 3N finetune quant should you choose?

F16 (13.7 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegemma3n
Parameters6.87B
Layers35
Trained context32,768 tokens
KV cache (fp16)70 KB per token

Source

Quantized bysamanta-scratch
FamilyGemma
Downloads (HF)8
Last updated2025-11-07

Frequently asked questions about gemma 3N finetune

How much VRAM does gemma 3N finetune need?

About 14.8 GB at F16 with an 8K context window. That is the 13.7 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 gemma 3N finetune on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 14.8 GB, so you would need a larger GPU or CPU offloading.

What is the file size of gemma 3N finetune GGUF?

It depends on the quant: F16 is 13.7 GB.

What context length does gemma 3N finetune support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.6 GB at 8K and 2.3 GB at 32K.

Where can I download gemma 3N finetune GGUF?

The files are on Hugging Face in the samanta-scratch/gemma-3N-finetune-GGUF 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 Gemma models

All Gemma →

Other small models

All small models →