GE

gemma-4-31B-it

GemmaGGUF by sphaelaUpdated 2026-04-24
Download on Hugging Face
Parameters30.7B
Context256K
Layers60
Architecturegemma4
Smallest quant10.8 GB
Quick answer

gemma-4-31B-it needs about 50.4 GB of memory at Q4_K_M (a 17.7 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 15 quants, from 10.8 GB (Q2_K_S) to 32.6 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 128.8 GB.

gemma-4-31B-it is a 30.7B-parameter Gemma model in GGUF format, quantized by sphaela. Its trained context length is 256K tokens. The repository has 15 quant files, from 10.8 GB (Q2_K_S) to 32.6 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K_S10.8 GB 43.5 GB
Too big Get file →
Q3_K_L13.8 GB 46.5 GB
Too big Get file →
Q3_K_M13.8 GB 46.5 GB
Too big Get file →
Q3_K_S13.8 GB 46.5 GB
Too big Get file →
Q4_017.7 GB 50.4 GB
Too big Get file →
Q4_K_M17.7 GB 50.4 GB
Too big Get file →
Q4_K_S17.7 GB 50.4 GB
Too big Get file →
Q2_K18.0 GB 50.7 GB
Too big Get file →
Q4_119.5 GB 52.2 GB
Too big Get file →
Q5_021.3 GB 54.0 GB
Too big Get file →
Q5_K_M21.3 GB 54.0 GB
Too big Get file →
Q5_K_S21.3 GB 54.0 GB
Too big Get file →
Q5_123.1 GB 55.9 GB
Too big Get file →
Q6_K25.2 GB 57.9 GB
Too big Get file →
Q8_032.6 GB 65.3 GB
Too big Get file →

What GPU do you need for gemma-4-31B-it?

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_L (13.8 GB file, about 46.5 GB in use).

Which gemma-4-31B-it quant should you choose?

Q4_K_M is the usual starting point for gemma-4-31B-it: it balances file size and quality well. Here it is a 17.7 GB file.

The Q8_0 file is 32.6 GB, about 1.8 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.

If memory is tight, the smallest file is Q2_K_S at 10.8 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

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 bysphaela
FamilyGemma
Licenseapache-2.0
Downloads (HF)408
Last updated2026-04-24

Frequently asked questions about gemma-4-31B-it

How much VRAM does gemma-4-31B-it need?

About 50.4 GB at Q4_K_M with an 8K context window. That is the 17.7 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-4-31B-it on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 43.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of gemma-4-31B-it GGUF?

It depends on the quant: Q2_K_S is 10.8 GB, Q3_K_L is 13.8 GB, Q3_K_M is 13.8 GB, Q3_K_S is 13.8 GB, Q4_0 is 17.7 GB, Q4_K_M is 17.7 GB and 9 more.

What context length does gemma-4-31B-it 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 GGUF?

The files are on Hugging Face in the sphaela/gemma-4-31B-it-AutoRound-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 gemma-4-31B-it 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 sphaela

All by sphaela →

More Gemma models

All Gemma →

Other medium models

All medium models →