GE

gemma 4 31B it aard 3bit

GemmaGGUF by aaardparkUpdated 2026-04-12
Download on Hugging Face
Parameters30.7B
Context256K
Layers60
Architecturegemma4
Smallest quant15.3 GB
Quick answer

gemma 4 31B it aard 3bit needs about 48.0 GB of memory at Q3_K_M (a 15.3 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 128.8 GB.

gemma 4 31B it aard 3bit is a 30.7B-parameter Gemma model in GGUF format, quantized by aaardpark. Its trained context length is 256K tokens. The repository has 1 quant file, from 15.3 GB (Q3_K_M) to 15.3 GB (Q3_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_M15.3 GB 48.0 GB
Too big Get file →

What GPU do you need for gemma 4 31B it aard 3bit?

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 Q3_K_M (15.3 GB file, about 48.0 GB in use).

Which gemma 4 31B it aard 3bit quant should you choose?

Q3_K_M (15.3 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegemma4
Parameters30.7B
Layers60
Trained context262,144 tokens
KV cache (fp16)3840 KB per token

Source

Quantized byaaardpark
FamilyGemma
Licensegemma
Downloads (HF)44
Last updated2026-04-12

Frequently asked questions about gemma 4 31B it aard 3bit

How much VRAM does gemma 4 31B it aard 3bit need?

About 48.0 GB at Q3_K_M with an 8K context window. That is the 15.3 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 4 31B it aard 3bit on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 48.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of gemma 4 31B it aard 3bit GGUF?

It depends on the quant: Q3_K_M is 15.3 GB.

What context length does gemma 4 31B it aard 3bit support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 32.2 GB at 8K and 128.8 GB at 32K.

Where can I download gemma 4 31B it aard 3bit GGUF?

The files are on Hugging Face in the aaardpark/gemma-4-31B-it_aard-3bit repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does gemma 4 31B it aard 3bit 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 gemma-4-31B-it

Similar models

Browse all →

More from aaardpark

All by aaardpark →

More Gemma models

All Gemma →

Other medium models

All medium models →