GE

AriannaV4_merged

GemmaGGUF by SurgeFFUpdated 2026-08-30
Download on Hugging Face
Parameters11.9B
Context256K
Layers48
Architecturegemma4
Smallest quant3.9 GB
Quick answer

AriannaV4_merged needs about 20.8 GB of memory at Q4_K_M (a 7.4 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 28 quants, from 3.9 GB (IQ2_XS) to 23.8 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 51.5 GB.

AriannaV4_merged: a multimodal Gemma‑4 12B model for local use

AriannaV4_merged combines the google/gemma-4-12B weights with Surge’s Aria v4 merge. It supports text, image, audio, and video input and outputs text. The model is available in a full GGUF quant ladder for llama.cpp, Ollama, and LM Studio.

Good at

  • Multimodal reasoning
  • Text generation
  • Audio and vision understanding

Limits

  • License cc‑by‑nc‑sa‑4.0
  • No separate vision encoder
  • Large context window requires high memory

Best for

  • Local multimodal assistants
  • On‑device reasoning tasks
  • Audio‑visual content generation

Who it’s for. Developers and hobbyists who need a unified, multimodal LLM that runs locally. The model is suitable for laptops and servers with sufficient VRAM and RAM to handle the 12B parameter size.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_XS3.9 GB 17.3 GB
Too big Get file →
Q2_K4.8 GB 18.2 GB
Too big Get file →
Q2_K4.8 GB 18.2 GB
Too big Get file →
IQ3_XS5.3 GB 18.7 GB
Too big Get file →
Q3_K_S5.5 GB 18.9 GB
Too big Get file →
Q3_K_S5.5 GB 18.9 GB
Too big Get file →
IQ3_M5.7 GB 19.1 GB
Too big Get file →
Q3_K_M6.1 GB 19.5 GB
Too big Get file →
Q3_K_M6.1 GB 19.5 GB
Too big Get file →
Q3_K_L6.6 GB 20.0 GB
Too big Get file →
IQ4_XS6.7 GB 20.1 GB
Too big Get file →
IQ4_XS6.7 GB 20.1 GB
Too big Get file →
Q4_07.0 GB 20.4 GB
Too big Get file →
Q4_K_S7.0 GB 20.4 GB
Too big Get file →
Q4_K_S7.0 GB 20.4 GB
Too big Get file →
Q4_K_M7.4 GB 20.8 GB
Too big Get file →
Q4_K_M7.4 GB 20.8 GB
Too big Get file →
Q5_08.3 GB 21.7 GB
Too big Get file →
Q5_K_S8.3 GB 21.7 GB
Too big Get file →
Q5_K_S8.3 GB 21.7 GB
Too big Get file →
Q5_K_M8.5 GB 21.9 GB
Too big Get file →
Q5_K_M8.5 GB 21.9 GB
Too big Get file →
Q6_K9.8 GB 23.2 GB
Too big Get file →
Q6_K9.8 GB 23.2 GB
Too big Get file →
Q8_012.7 GB 26.1 GB
Too big Get file →
Q8_012.7 GB 26.1 GB
Too big Get file →
F1623.8 GB 37.2 GB
Too big Get file →
F1623.8 GB 37.2 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (file size 7.38 GB, estimated 20.8 GB memory at 8K context). For 16 GB VRAM, Q5_K_M (file size 8.55 GB, estimated 21.9 GB memory). For 32 GB VRAM, Q6_K (file size 9.79 GB, estimated 23.2 GB memory).

What GPU do you need for AriannaV4_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: the best quant that fits is Q6_K (9.8 GB file, about 23.2 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (12.7 GB file, about 26.1 GB in use).
  • 48 GB VRAM: the best quant that fits is F16 (23.8 GB file, about 37.2 GB in use).

Which AriannaV4_merged quant should you choose?

Q4_K_M is the usual starting point for AriannaV4_merged: it balances file size and quality well. Here it is a 7.4 GB file.

The Q8_0 file is 12.7 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 IQ2_XS at 3.9 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
Parameters11.9B
Layers48
Trained context262,144 tokens
KV cache (fp16)1536 KB per token

Source

Quantized bySurgeFF
FamilyGemma
Downloads (HF)987
Last updated2026-08-30

Frequently asked questions about AriannaV4_merged

How much VRAM does AriannaV4_merged need?

About 20.8 GB at Q4_K_M with an 8K context window. That is the 7.4 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 AriannaV4_merged on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 17.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of AriannaV4_merged GGUF?

It depends on the quant: IQ2_XS is 3.9 GB, Q2_K is 4.8 GB, Q2_K is 4.8 GB, IQ3_XS is 5.3 GB, Q3_K_S is 5.5 GB, Q3_K_S is 5.5 GB and 22 more.

What context length does AriannaV4_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 12.9 GB at 8K and 51.5 GB at 32K.

Where can I download AriannaV4_merged GGUF?

The files are on Hugging Face in the SurgeFF/AriannaV4 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does AriannaV4_merged use?

Hugging Face lists the license as cc-by-nc-sa-4.0. 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 AriannaV4_merged on 8 GB VRAM?

Use the Q4_K_M quant, which requires approximately 20.8 GB memory at 8K context. 8 GB VRAM is insufficient for this model.

Does the model support vision input?

Yes, the model has detected vision ability and can process image input natively.

What license applies to this model?

The model is licensed under cc‑by‑nc‑sa‑4.0.

Other GGUFs of gemma-4-12B

Similar models

Browse all →

More from SurgeFF

All by SurgeFF →

More Gemma models

All Gemma →

Other medium models

All medium models →