LL

video llava

LLaVAGGUF by AnasMohamedUpdated 2024-12-27
Download on Hugging Face
Parameters6.74B
Context4K
Layers32
Architecturellama
Smallest quant4.1 GB
Quick answer

video llava needs about 8.9 GB of memory at F32 (a 4.1 GB file) with an 8K context window, so it fits on a 12 GB GPU.

video llava is a 6.74B-parameter LLaVA model in GGUF format, quantized by AnasMohamed. Its trained context length is 4K tokens. The repository has 1 quant file, from 4.1 GB (F32) to 4.1 GB (F32).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F324.1 GB 6.7 GB
Fits Get file →

What GPU do you need for video llava?

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: the best quant that fits is F32 (4.1 GB file, about 8.9 GB in use).

Which video llava quant should you choose?

F32 (4.1 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

Architecturellama
Parameters6.74B
Layers32
Trained context4,096 tokens
KV cache (fp16)512 KB per token

Source

Quantized byAnasMohamed
FamilyLLaVA
Downloads (HF)126
Last updated2024-12-27

Frequently asked questions about video llava

How much VRAM does video llava need?

About 8.9 GB at F32 with an 8K context window. That is the 4.1 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 video llava on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 8.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of video llava GGUF?

It depends on the quant: F32 is 4.1 GB.

What context length does video llava support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 4.3 GB at 8K and 2.1 GB at 4K.

Where can I download video llava GGUF?

The files are on Hugging Face in the AnasMohamed/video-llava 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 LLaVA models

All LLaVA →

Other small models

All small models →