OM

OmniSVG1.1_8B

OmnisvgGGUF by amandabensonUpdated 2026-08-11
Download on Hugging Face
Parameters7.94B
Context125K
Layers28
Architectureqwen2vl
Smallest quant15.9 GB
Quick answer

OmniSVG1.1_8B needs about 16.9 GB of memory at BF16 (a 15.9 GB file) with an 8K context window, so it fits on a 24 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 1.9 GB.

OmniSVG1.1_8B is a 7.94B-parameter Omnisvg model in GGUF format, quantized by amandabenson. Its trained context length is 125K tokens. The repository has 1 quant file, from 15.9 GB (BF16) to 15.9 GB (BF16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
BF1615.9 GB 16.9 GB
Too big Get file →

What GPU do you need for OmniSVG1.1_8B?

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 BF16 (15.9 GB file, about 16.9 GB in use).

Which OmniSVG1.1_8B quant should you choose?

BF16 (15.9 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen2vl
Parameters7.94B
Layers28
Trained context128,000 tokens
KV cache (fp16)56 KB per token

Source

Quantized byamandabenson
FamilyOmnisvg
Downloads (HF)5
Last updated2026-08-11

Frequently asked questions about OmniSVG1.1_8B

How much VRAM does OmniSVG1.1_8B need?

About 16.9 GB at BF16 with an 8K context window. That is the 15.9 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 OmniSVG1.1_8B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 16.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of OmniSVG1.1_8B GGUF?

It depends on the quant: BF16 is 15.9 GB.

What context length does OmniSVG1.1_8B support?

The GGUF header lists a trained context length of 128,000 tokens (125K). The KV cache grows with the context you use: about 0.5 GB at 8K and 1.9 GB at 32K.

Where can I download OmniSVG1.1_8B GGUF?

The files are on Hugging Face in the amandabenson/OmniSVG1.1_8B-GGUF-fork repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More from amandabenson

All by amandabenson →

More Omnisvg models

All Omnisvg →

Other small models

All small models →