GE

atlas gemma4 31b v21

GemmaGGUF by kintsugicollectiveUpdated 2026-07-04
Download on Hugging Face
Parameters30.7B
Context256K
Layers60
Architecturegemma4
Smallest quant18.7 GB
Quick answer

atlas gemma4 31b v21 needs about 51.4 GB of memory at Q4_K_M (a 18.7 GB file) with an 8K context window, which is more than a 48 GB GPU holds. Longer context needs more: at 32K tokens the KV cache alone adds about 128.8 GB.

atlas gemma4 31b v21 is a 30.7B-parameter Gemma model in GGUF format, quantized by kintsugicollective. Its trained context length is 256K tokens. The repository has 1 quant file, from 18.7 GB (Q4_K_M) to 18.7 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M18.7 GB 51.4 GB
Too big Get file →

What GPU do you need for atlas gemma4 31b v21?

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: no quant fits at an 8K context.

Which atlas gemma4 31b v21 quant should you choose?

Q4_K_M is the usual starting point for atlas gemma4 31b v21: it balances file size and quality well. Here it is a 18.7 GB file.

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 bykintsugicollective
FamilyGemma
Licenseapache-2.0
Downloads (HF)55
Last updated2026-07-04

Frequently asked questions about atlas gemma4 31b v21

How much VRAM does atlas gemma4 31b v21 need?

About 51.4 GB at Q4_K_M with an 8K context window. That is the 18.7 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 atlas gemma4 31b v21 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 51.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of atlas gemma4 31b v21 GGUF?

It depends on the quant: Q4_K_M is 18.7 GB.

What context length does atlas gemma4 31b v21 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 atlas gemma4 31b v21 GGUF?

The files are on Hugging Face in the kintsugicollective/atlas-gemma4-31b-v21-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 atlas gemma4 31b v21 use?

Hugging Face lists the license as apache-2.0. 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 kintsugicollective

All by kintsugicollective →

More Gemma models

All Gemma →

Other medium models

All medium models →