SV

SVILA 1 12B

SvilaGGUF by mradermacherUpdated 2026-08-10
Download on Hugging Face
Parameters12.8B
Context128K
Layers48
Architecturegemma3
Smallest quant0.0 GB
Quick answer

SVILA 1 12B needs about 11.6 GB of memory at Q4_K_M (a 7.9 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 25 quants, from 0.0 GB to 10.5 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 12.9 GB.

SVILA 1 12B – a vision language model for Slovenian

SVILA 1 12B is a 12.8 billion parameter model based on gemma3. It supports vision tasks and was fine‑tuned on a curated Slovenian text‑image dataset. The model is released under the MIT license.

Good at

  • Vision‑language inference
  • Instruction following
  • Multimodal generation

Limits

  • No vision support in non‑vision quant files
  • Requires 8 k context for estimates
  • Large VRAM needed for higher quants

Best for

  • Image captioning in Slovenian
  • Multimodal chatbots
  • Data annotation tools

Who it’s for. Developers building Slovenian‑centric vision‑language applications. Researchers needing a fine‑tuned Slovenian model for multimodal tasks. Hobbyists looking for a free, MIT‑licensed model.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 3.7 GB
Fits Get file →
IQ1_S3.3 GB 7.0 GB
Fits Get file →
IQ1_M3.5 GB 7.2 GB
Tight Get file →
IQ2_XXS3.9 GB 7.6 GB
Tight Get file →
IQ2_XS4.2 GB 7.9 GB
Tight Get file →
IQ2_S4.5 GB 8.2 GB
Too big Get file →
IQ2_M4.7 GB 8.5 GB
Too big Get file →
Q2_K_S4.8 GB 8.5 GB
Too big Get file →
Q2_K5.1 GB 8.8 GB
Too big Get file →
IQ3_XXS5.2 GB 8.9 GB
Too big Get file →
IQ3_XS5.6 GB 9.4 GB
Too big Get file →
IQ3_S5.9 GB 9.6 GB
Too big Get file →
Q3_K_S5.9 GB 9.6 GB
Too big Get file →
IQ3_M6.1 GB 9.8 GB
Too big Get file →
Q3_K_M6.4 GB 10.2 GB
Too big Get file →
Q3_K_L6.9 GB 10.6 GB
Too big Get file →
IQ4_XS7.1 GB 10.8 GB
Too big Get file →
IQ4_NL7.5 GB 11.2 GB
Too big Get file →
Q4_07.5 GB 11.2 GB
Too big Get file →
Q4_K_S7.5 GB 11.2 GB
Too big Get file →
Q4_K_M7.9 GB 11.6 GB
Too big Get file →
Q4_18.2 GB 11.9 GB
Too big Get file →
Q5_K_S8.9 GB 12.6 GB
Too big Get file →
Q5_K_M9.1 GB 12.9 GB
Too big Get file →
Q6_K10.5 GB 14.2 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (3.28 GB, 7 GB memory) or IQ1_M (3.5 GB, 7.2 GB memory). For 12 GB VRAM, IQ4_K_M (7.87 GB, 11.6 GB memory) or Q5_K_S (8.92 GB, 12.6 GB memory) are suitable. For 16 GB VRAM, Q6_K (10.49 GB, 14.2 GB memory) offers the highest quality.

What GPU do you need for SVILA 1 12B?

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 the main file (0.0 GB file, about 3.7 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 3.7 GB in use).
  • 8 GB VRAM: the best quant that fits is IQ2_XS (4.2 GB file, about 7.9 GB in use).
  • 12 GB VRAM: the best quant that fits is Q4_1 (8.2 GB file, about 11.9 GB in use).
  • 16 GB VRAM: the best quant that fits is Q6_K (10.5 GB file, about 14.2 GB in use).

Which SVILA 1 12B quant should you choose?

Q4_K_M is the usual starting point for SVILA 1 12B: it balances file size and quality well. Here it is a 7.9 GB file.

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

Architecturegemma3
Parameters12.8B
Layers48
Trained context131,072 tokens
KV cache (fp16)384 KB per token

Source

Quantized bymradermacher
FamilySvila
Licensemit
Downloads (HF)963
Last updated2026-08-10

Frequently asked questions about SVILA 1 12B

How much VRAM does SVILA 1 12B need?

About 11.6 GB at Q4_K_M with an 8K context window. That is the 7.9 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 SVILA 1 12B on an 8 GB GPU?

Yes, with IQ2_XS: the 4.2 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of SVILA 1 12B GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 3.3 GB, IQ1_M is 3.5 GB, IQ2_XXS is 3.9 GB, IQ2_XS is 4.2 GB, IQ2_S is 4.5 GB and 19 more.

What context length does SVILA 1 12B support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 3.2 GB at 8K and 12.9 GB at 32K.

Where can I download SVILA 1 12B GGUF?

The files are on Hugging Face in the mradermacher/SVILA-1-12B-i1-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 SVILA 1 12B use?

Hugging Face lists the license as mit. 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 SVILA 1 12B on 8 GB VRAM?

Use IQ1_S or IQ1_M quant files; they require about 7 GB memory at 8 k context.

Does the model support vision tasks?

Yes, it is a vision language model; vision support is available in the provided quant files.

What license is the model released under?

The model is released under the MIT license.

Other GGUFs of SVILA-1-12B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Svila models

All Svila →

Other medium models

All medium models →