GE

gemma 4 31B it Q4 K local Q6 K global

GemmaGGUF by DZgasUpdated 2026-10-01
Download on Hugging Face
Parameters30.7B
Context128K
Layers4
Architecturegemma4-assistant
Smallest quant0.3 GB
Quick answer

gemma 4 31B it Q4 K local Q6 K global needs about 20.6 GB of memory at Q4_K (a 19.0 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 11 quants, from 0.3 GB to 26.9 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Gemma 4 31B it Q4 K local Q6 K global – a large multimodal LLM

Gemma 4 31B it Q4 K local Q6 K global is a 30.7 billion‑parameter model with a 131072‑token context window. It supports text and image input and outputs text. The model is available in several GGUF quantizations.

Good at

  • Large‑context text generation
  • Multimodal reasoning with images
  • Instruction‑tuned dialogue

Limits

  • No official license listed
  • No audio support
  • Requires llama.cpp b9918

Best for

  • Long‑form content creation
  • Multimodal QA
  • Code generation

Who it’s for. Developers and researchers who need a high‑capacity multimodal model for local deployment. The model is suitable for servers or workstations with sufficient GPU memory.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.3 GB 1.8 GB
Fits Get file →
Q6_K0.4 GB 1.9 GB
Fits Get file →
Q6_K0.4 GB 2.0 GB
Fits Get file →
Q4_K_XL14.2 GB 15.8 GB
Too big Get file →
Q4_K19.0 GB 20.6 GB
Too big Get file →
Q4_K19.0 GB 20.6 GB
Too big Get file →
Q5_K_M21.2 GB 22.7 GB
Too big Get file →
Q4_K_L21.5 GB 23.0 GB
Too big Get file →
Q4_K_L21.5 GB 23.0 GB
Too big Get file →
Q6_K23.2 GB 24.7 GB
Too big Get file →
Q8_026.9 GB 28.4 GB
Too big Get file →

For 8 GB VRAM, use the Q6_K quant (0.36 GB file, ~1.9 GB memory at 8 k context). For 16 GB VRAM, Q4_K_XL (14.25 GB file, ~15.8 GB memory) or Q4_K (19.03 GB file, ~20.6 GB memory) are options. For 24 GB VRAM, Q5_K_M (21.15 GB file, ~22.7 GB memory) or Q4_K_L (21.45 GB file, ~23 GB memory) fit.

What GPU do you need for gemma 4 31B it Q4 K local Q6 K global?

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 Q6_K (0.4 GB file, about 2.0 GB in use).
  • 6 GB VRAM: the best quant that fits is Q6_K (0.4 GB file, about 2.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q6_K (0.4 GB file, about 2.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (0.4 GB file, about 2.0 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_K_XL (14.2 GB file, about 15.8 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_K_L (21.5 GB file, about 23.0 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (26.9 GB file, about 28.4 GB in use).

Which gemma 4 31B it Q4 K local Q6 K global quant should you choose?

Q4_K (19.0 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

If memory is tight, the smallest file is the first one in the table at 0.3 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-assistant
Parameters30.7B
Layers4
Trained context131,072 tokens
KV cache (fp16)128 KB per token

Source

Quantized byDZgas
FamilyGemma
Downloads (HF)311
Last updated2026-10-01

Frequently asked questions about gemma 4 31B it Q4 K local Q6 K global

How much VRAM does gemma 4 31B it Q4 K local Q6 K global need?

About 20.6 GB at Q4_K with an 8K context window. That is the 19.0 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 Q4 K local Q6 K global on an 8 GB GPU?

Yes, with Q6_K: the 0.4 GB file needs about 2.0 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 Q4 K local Q6 K global GGUF?

It depends on the quant: file is 0.3 GB, Q6_K is 0.4 GB, Q6_K is 0.4 GB, Q4_K_XL is 14.2 GB, Q4_K is 19.0 GB, Q4_K is 19.0 GB and 5 more.

What context length does gemma 4 31B it Q4 K local Q6 K global support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download gemma 4 31B it Q4 K local Q6 K global GGUF?

The files are on Hugging Face in the DZgas/gemma-4-31B-it-Q4_K-local-Q6_K-global-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run this model on 8 GB VRAM?

Yes, the Q6_K quant uses about 1.9 GB memory at 8 k context, fitting within 8 GB VRAM.

Does this model support image input?

Yes, the model has vision capability and can process images.

Which quantization is best for 16 GB VRAM?

Use Q4_K_XL (14.25 GB file, ~15.8 GB memory) or Q4_K (19.03 GB file, ~20.6 GB memory).

Other GGUFs of gemma-4-31B-it

Similar models

Browse all →

More from DZgas

All by DZgas →

More Gemma models

All Gemma →

Other medium models

All medium models →