GE

Aura 4o Refresh Gemma 4 31B Merged

GemmaGGUF by mradermacherUpdated 2026-10-29
Download on Hugging Face
Parameters30.7B
Context256K
Layers60
Architecturegemma4
Smallest quant11.9 GB
Quick answer

Aura 4o Refresh Gemma 4 31B Merged needs about 51.4 GB of memory at Q4_K_M (a 18.7 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 11 quants, from 11.9 GB (Q2_K) to 32.6 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 128.8 GB.

Aura 4o Refresh Gemma 4 31B Merged – a 30.7B parameter Gemma4 model with partial vision

Aura 4o Refresh Gemma 4 31B Merged is a 30.7B parameter Gemma4 model that merges a V1 LoRA into a BF16 base. It supports reasoning, tools, and vision, though vision is partially functional. The model is released under apache-2.0 and is available as multiple GGUF quantizations.

Good at

  • Reasoning and tool use
  • Partial vision support
  • Large context of 262144 tokens

Limits

  • Vision is inconsistent
  • Requires 8k context for memory estimates
  • No training data details

Best for

  • Chat assistants needing large context
  • Tool‑enabled workflows
  • Casual image input

Who it’s for. Developers and researchers who need a large Gemma4 model with a V1 LoRA voice and can tolerate partial vision limitations. Suitable for local or serverless inference using llama.cpp.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K11.9 GB 44.6 GB
Too big Get file →
Q3_K_S13.8 GB 46.5 GB
Too big Get file →
Q3_K_M15.3 GB 48.0 GB
Too big Get file →
Q3_K_L16.6 GB 49.3 GB
Too big Get file →
IQ4_XS16.9 GB 49.6 GB
Too big Get file →
Q4_K_S17.8 GB 50.5 GB
Too big Get file →
Q4_K_M18.7 GB 51.4 GB
Too big Get file →
Q5_K_S21.3 GB 54.0 GB
Too big Get file →
Q5_K_M21.8 GB 54.6 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 →

For 8 GB VRAM, use Q2_K (file size 11.92 GB, estimated memory 44.6 GB at 8k context). For 16 GB VRAM, Q4_K_M (file size 18.69 GB, estimated memory 51.4 GB). For 32 GB VRAM, Q8_0 (file size 32.64 GB, estimated memory 65.3 GB).

What GPU do you need for Aura 4o Refresh Gemma 4 31B Merged?

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 (15.3 GB file, about 48.0 GB in use).

Which Aura 4o Refresh Gemma 4 31B Merged quant should you choose?

Q4_K_M is the usual starting point for Aura 4o Refresh Gemma 4 31B Merged: it balances file size and quality well. Here it is a 18.7 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 Q2_K at 11.9 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 bymradermacher
FamilyGemma
Licenseapache-2.0
Downloads (HF)946
Last updated2026-10-29

Frequently asked questions about Aura 4o Refresh Gemma 4 31B Merged

How much VRAM does Aura 4o Refresh Gemma 4 31B Merged need?

About 51.4 GB at Q4_K_M with an 8K context window. That is the 18.7 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 Aura 4o Refresh Gemma 4 31B Merged on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 44.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Aura 4o Refresh Gemma 4 31B Merged GGUF?

It depends on the quant: Q2_K is 11.9 GB, Q3_K_S is 13.8 GB, Q3_K_M is 15.3 GB, Q3_K_L is 16.6 GB, IQ4_XS is 16.9 GB, Q4_K_S is 17.8 GB and 5 more.

What context length does Aura 4o Refresh Gemma 4 31B Merged 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 Aura 4o Refresh Gemma 4 31B Merged GGUF?

The files are on Hugging Face in the mradermacher/Aura-4o-Refresh-Gemma-4-31B-Merged-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 Aura 4o Refresh Gemma 4 31B Merged 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 Aura 4o Refresh Gemma 4 31B Merged on 8 GB VRAM?

No, the smallest quant requires at least 44.6 GB of VRAM at 8k context. You would need a larger GPU or a smaller context.

Is the vision capability reliable?

Vision is partially functional and inconsistent due to the base model’s abliteration. It is suitable only for casual image input.

What license does this model use?

The model is released under apache-2.0.

Other GGUFs of Aura-4o-Refresh-Gemma-4-31B-Merged

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Gemma models

All Gemma →

Other medium models

All medium models →