GE

Gemma-4-31B-It

GemmaGGUF by unslothUpdated 2026-07-17
Download on Hugging Face
Parameters30.7B
Context256K
Layers60
Architecturegemma4
Smallest quant0.5 GB
Quick answer

Gemma-4-31B-It needs about 51.0 GB of memory at Q4_K_M (a 18.3 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 26 quants, from 0.5 GB (Q8_0) to 61.4 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 128.8 GB.

Gemma‑4‑31B‑It: 31‑billion‑parameter multimodal instruction‑tuned model

Gemma‑4‑31B‑It is a 31‑billion‑parameter instruction‑tuned model from the Gemma‑4 family. It supports text and image input and generates text output. The model offers a context window of up to 256 K tokens and is licensed under Apache 2.0.

Good at

  • Multimodal text‑image understanding
  • Large‑context reasoning
  • Instruction‑driven dialogue

Limits

  • Requires high VRAM for full precision
  • No native audio support
  • License allows open use but requires attribution

Best for

  • Developers building multimodal chatbots
  • Researchers testing large‑context reasoning
  • Edge deployments with sufficient GPU memory

Who it’s for. The model is suited for developers and researchers who need a large, multimodal instruction‑tuned model with a long context window. It is ideal for applications that require detailed reasoning over extended text and image inputs.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_00.5 GB 33.2 GB
Too big Get file →
—0.5 GB 33.2 GB
Too big Get file →
BF161.0 GB 33.7 GB
Too big Get file →
F161.0 GB 33.7 GB
Too big Get file →
IQ2_XXS8.5 GB 41.2 GB
Too big Get file →
IQ2_M10.8 GB 43.5 GB
Too big Get file →
Q2_K_XL11.8 GB 44.5 GB
Too big Get file →
IQ3_XXS11.8 GB 44.6 GB
Too big Get file →
Q3_K_S13.2 GB 45.9 GB
Too big Get file →
Q3_K_M14.7 GB 47.4 GB
Too big Get file →
Q3_K_XL15.4 GB 48.1 GB
Too big Get file →
IQ4_XS16.4 GB 49.1 GB
Too big Get file →
IQ4_NL17.3 GB 50.0 GB
Too big Get file →
Q4_017.3 GB 50.1 GB
Too big Get file →
Q4_K_S17.4 GB 50.1 GB
Too big Get file →
Q4_K_M18.3 GB 51.0 GB
Too big Get file →
Q4_K_XL18.8 GB 51.5 GB
Too big Get file →
Q4_119.1 GB 51.8 GB
Too big Get file →
Q5_K_S21.1 GB 53.8 GB
Too big Get file →
Q5_K_M21.7 GB 54.4 GB
Too big Get file →
Q5_K_XL21.9 GB 54.6 GB
Too big Get file →
Q6_K25.2 GB 57.9 GB
Too big Get file →
Q6_K_XL27.5 GB 60.2 GB
Too big Get file →
Q8_032.6 GB 65.3 GB
Too big Get file →
Q8_K_XL35.0 GB 67.7 GB
Too big Get file →
BF1661.4 GB (2 parts) 94.1 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_S (17.4 GB file, ~50 GB memory). For 16 GB VRAM, Q4_K_M (18.32 GB file, ~51 GB memory). For 24 GB VRAM, Q5_K_S (21.12 GB file, ~53.8 GB memory). Memory estimates are approximate.

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_M (14.7 GB file, about 47.4 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 18.3 GB file.

The Q8_0 file is 0.5 GB, about 0.0 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 Q8_0 at 0.5 GB, with the quality trade-offs that come with fewer bits. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

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 byunsloth
FamilyGemma
Licenseapache-2.0
Downloads (HF)269,716
Last updated2026-07-17

Frequently asked questions about Gemma-4-31B-It

How much VRAM does Gemma-4-31B-It need?

About 51.0 GB at Q4_K_M with an 8K context window. That is the 18.3 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 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 33.2 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: Q8_0 is 0.5 GB, file is 0.5 GB, BF16 is 1.0 GB, F16 is 1.0 GB, IQ2_XXS is 8.5 GB, IQ2_M is 10.8 GB and 20 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 unsloth/gemma-4-31B-it-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.

Can I run Gemma‑4‑31B‑It on a laptop with 8 GB VRAM?

Use a Q4_K_S or Q4_K_M quantized file; the model will need ~50 GB of VRAM at 8 k context, so it is not feasible on 8 GB VRAM.

Does the model support audio input?

Audio is supported only on smaller Gemma‑4 models; Gemma‑4‑31B‑It does not support audio.

What license applies to this model?

The model is released under the Apache 2.0 license, allowing free use with attribution.

Other GGUFs of gemma-4-31B-it

Similar models

Browse all →

More from unsloth

All by unsloth →

More Gemma models

All Gemma →

Other medium models

All medium models →