GE

gemma-4-31B-it

GemmaGGUF by ggml-orgUpdated 2026-10-19
Download on Hugging Face
Parameters30.7B
Context256K
Layers4
Architecturegemma4-assistant
Smallest quant0.3 GB
Quick answer

gemma-4-31B-it needs about 4.3 GB of memory at Q8_0 (a 1.6 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 8 quants, from 0.3 GB (Q4_0) to 61.4 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.

Gemma 4 31B instruction-tuned model with 256K context

Gemma 4 31B‑it is a 30.7B‑parameter instruction‑tuned model from Google DeepMind. It supports multimodal input, including vision, and has a 262144‑token context window. The model is released under Apache‑2.0 and is available in several GGUF quantizations.

Good at

  • Large context handling
  • Multimodal vision support
  • Instruction‑following

Limits

  • No audio support
  • Requires large VRAM for high‑precision quants
  • No native video support

Best for

  • Complex reasoning tasks
  • Long‑form content generation
  • Multimodal data analysis

Who it’s for. Developers and researchers needing a high‑capacity, multimodal LLM for local deployment. The model is suitable for environments with sufficient GPU memory and for applications that require extended context and instruction compliance.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_00.3 GB 2.9 GB
Fits Get file →
Q8_00.5 GB 3.2 GB
Fits Get file →
BF161.0 GB 3.6 GB
Fits Get file →
Q8_01.6 GB 4.3 GB
Fits Get file →
BF163.1 GB 5.7 GB
Fits Get file →
Q4_018.0 GB 20.6 GB
Too big Get file →
Q8_032.6 GB 35.3 GB
Too big Get file →
BF1661.4 GB 64.1 GB
Too big Get file →

For 8 GB VRAM, use Q4_0 (0.28 GB, 2.9 GB memory at 8 k context). For 16 GB VRAM, Q8_0 (0.51 GB, 3.2 GB memory) or BF16 (0.95 GB, 3.6 GB memory) are suitable. For 32 GB VRAM, the 1.65 GB Q8_0 (4.3 GB memory) or 3.09 GB BF16 (5.7 GB memory) options are recommended. Larger quants exceed typical consumer GPU limits.

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: the best quant that fits is BF16 (1.0 GB file, about 3.6 GB in use).
  • 6 GB VRAM: the best quant that fits is BF16 (3.1 GB file, about 5.7 GB in use).
  • 8 GB VRAM: the best quant that fits is BF16 (3.1 GB file, about 5.7 GB in use).
  • 12 GB VRAM: the best quant that fits is BF16 (3.1 GB file, about 5.7 GB in use).
  • 16 GB VRAM: the best quant that fits is BF16 (3.1 GB file, about 5.7 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_0 (18.0 GB file, about 20.6 GB in use).
  • 32 GB VRAM: the best quant that fits is Q4_0 (18.0 GB file, about 20.6 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (32.6 GB file, about 35.3 GB in use).

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

Q8_0 (1.6 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

If memory is tight, the smallest file is Q4_0 at 0.3 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegemma4-assistant
Parameters30.7B
Layers4
Trained context262,144 tokens
KV cache (fp16)256 KB per token

Source

Quantized byggml-org
FamilyGemma
Licenseapache-2.0
Downloads (HF)38,834
Last updated2026-10-19

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

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

About 4.3 GB at Q8_0 with an 8K context window. That is the 1.6 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?

Yes, with BF16: the 3.1 GB file needs about 5.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

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

It depends on the quant: Q4_0 is 0.3 GB, Q8_0 is 0.5 GB, BF16 is 1.0 GB, Q8_0 is 1.6 GB, BF16 is 3.1 GB, Q4_0 is 18.0 GB and 2 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 2.1 GB at 8K and 8.6 GB at 32K.

Where can I download gemma-4-31B-it GGUF?

The files are on Hugging Face in the ggml-org/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?

Yes, using the Q4_0 quant (0.28 GB file) which requires about 2.9 GB VRAM at 8 k context.

Does this model support audio input?

No, audio support is only available on smaller Gemma 4 variants (E2B, E4B, 12B).

What license applies to this model?

The model is released under the Apache‑2.0 license.

Other GGUFs of gemma-4-31B-it

Similar models

Browse all →

More from ggml-org

All by ggml-org →

More Gemma models

All Gemma →

Other medium models

All medium models →