GE

another bigger gemma3 abomination

GemmaGGUF by ArtusDevUpdated 2025-04-12
Download on Hugging Face
Parameters17.1B
Context128K
Layers72
Architecturegemma3
Smallest quant10.5 GB
Quick answer

another bigger gemma3 abomination needs about 15.9 GB of memory at Q4_K_M (a 10.5 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 3 quants, from 10.5 GB (Q4_K_M) to 18.2 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 19.3 GB.

another bigger gemma3 abomination is a 17.1B-parameter Gemma model in GGUF format, quantized by ArtusDev. Its trained context length is 128K tokens. The repository has 3 quant files, from 10.5 GB (Q4_K_M) to 18.2 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M10.5 GB 15.9 GB
Too big Get file →
Q5_K_M12.3 GB 17.6 GB
Too big Get file →
Q8_018.2 GB 23.6 GB
Too big Get file →

What GPU do you need for another bigger gemma3 abomination?

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 Q4_K_M (10.5 GB file, about 15.9 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (18.2 GB file, about 23.6 GB in use).

Which another bigger gemma3 abomination quant should you choose?

Q4_K_M is the usual starting point for another bigger gemma3 abomination: it balances file size and quality well. Here it is a 10.5 GB file.

The Q8_0 file is 18.2 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegemma3
Parameters17.1B
Layers72
Trained context131,072 tokens
KV cache (fp16)576 KB per token

Source

Quantized byArtusDev
FamilyGemma
Licensegemma
Downloads (HF)33
Last updated2025-04-12

Frequently asked questions about another bigger gemma3 abomination

How much VRAM does another bigger gemma3 abomination need?

About 15.9 GB at Q4_K_M with an 8K context window. That is the 10.5 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 another bigger gemma3 abomination on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 15.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of another bigger gemma3 abomination GGUF?

It depends on the quant: Q4_K_M is 10.5 GB, Q5_K_M is 12.3 GB, Q8_0 is 18.2 GB.

What context length does another bigger gemma3 abomination support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 4.8 GB at 8K and 19.3 GB at 32K.

Where can I download another bigger gemma3 abomination GGUF?

The files are on Hugging Face in the ArtusDev/another-bigger-gemma3-abomination-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 another bigger gemma3 abomination 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.

Similar models

Browse all →

More from ArtusDev

All by ArtusDev →

More Gemma models

All Gemma →

Other medium models

All medium models →