GE

gemma-4-31B-it

GemmaGGUF by MungertUpdated 2026-06-05
Download on Hugging Face
Parameters30.7B
Context256K
Layers60
Architecturegemma4
Smallest quant0.0 GB
Quick answer

gemma-4-31B-it needs about 52.0 GB of memory at Q4_K_M (a 19.3 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 23 quants, from 0.0 GB to 47.6 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 128.8 GB.

Gemma 4 31B instruction-tuned model with multimodal support

Gemma 4 31B is an instruction-tuned variant of the 31B Gemma model. It supports text and image input and generates text output. The model has a context window of up to 256K tokens and is released under Apache 2.0.

Good at

  • Multimodal text and image processing
  • Large context reasoning
  • Instruction following

Limits

  • No native vision support in quantized files
  • Requires large VRAM for full precision
  • License is Apache 2.0

Best for

  • Local inference on high‑end GPUs
  • Multimodal chat applications
  • Research prototyping

Who it’s for. Developers and researchers who need a large, instruction‑tuned multimodal model for local deployment. The model is suitable for environments with sufficient GPU memory and a need for extended context handling.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 32.7 GB
Too big Get file →
IQ1_S7.9 GB 40.6 GB
Too big Get file →
IQ2_XXS9.1 GB 41.8 GB
Too big Get file →
IQ1_M9.1 GB 41.8 GB
Too big Get file →
IQ2_XS10.1 GB 42.8 GB
Too big Get file →
IQ2_S10.8 GB 43.5 GB
Too big Get file →
IQ2_M11.4 GB 44.1 GB
Too big Get file →
Q2_K_S11.8 GB 44.5 GB
Too big Get file →
IQ3_XXS13.3 GB 46.0 GB
Too big Get file →
IQ3_XS13.5 GB 46.2 GB
Too big Get file →
Q3_K_S15.3 GB 48.0 GB
Too big Get file →
IQ3_M15.8 GB 48.5 GB
Too big Get file →
Q3_K_M15.8 GB 48.5 GB
Too big Get file →
Q4_018.0 GB 50.7 GB
Too big Get file →
Q4_K_S18.4 GB 51.1 GB
Too big Get file →
Q4_119.3 GB 52.0 GB
Too big Get file →
Q4_K_M19.3 GB 52.0 GB
Too big Get file →
Q5_021.7 GB 54.4 GB
Too big Get file →
Q5_K_M22.7 GB 55.4 GB
Too big Get file →
Q6_K_M25.5 GB 58.3 GB
Too big Get file →
Q8_032.6 GB 65.3 GB
Too big Get file →
BF1647.6 GB 80.3 GB
Too big Get file →
F1647.6 GB 80.3 GB
Too big Get file →

For 8 GB VRAM, use Q4_0 or Q4_K_S (file size 17.99 GB or 18.39 GB, memory ~50.7 GB or 51.1 GB). For 12 GB VRAM, Q5_0 or Q5_K_M (21.65 GB or 22.67 GB, memory ~54.4 GB or 55.4 GB). For 16 GB VRAM, Q6_K_M (25.54 GB, memory ~58.3 GB).

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_S (15.3 GB file, about 48.0 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 19.3 GB file.

The Q8_0 file is 32.6 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.

If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.

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 byMungert
FamilyGemma
Licenseapache-2.0
Downloads (HF)1,866
Last updated2026-06-05

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

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

About 52.0 GB at Q4_K_M with an 8K context window. That is the 19.3 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 32.7 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: file is 0.0 GB, IQ1_S is 7.9 GB, IQ2_XXS is 9.1 GB, IQ1_M is 9.1 GB, IQ2_XS is 10.1 GB, IQ2_S is 10.8 GB and 17 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 Mungert/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 8 GB VRAM?

The smallest quantizations (Q4_0, Q4_K_S) require about 50.7–51.1 GB VRAM at 8 k context, so 8 GB VRAM is insufficient.

What quantization gives the best trade‑off for 12 GB VRAM?

Q5_0 or Q5_K_M provide around 54.4–55.4 GB VRAM usage, which is close to 12 GB but still exceeds it; larger VRAM is needed.

Is the model licensed for commercial use?

The model is released under Apache 2.0, which permits commercial use with attribution.

Other GGUFs of gemma-4-31B

Similar models

Browse all →

More from Mungert

All by Mungert →

More Gemma models

All Gemma →

Other medium models

All medium models →