LL

LLaVA

LLaVAGGUF by HyperMinkUpdated 2024-05-22
Download on Hugging Face
Parameters6.74B
Context4K
Layers32
Architecturellama
Smallest quant4.1 GB
Quick answer

LLaVA needs about 8.9 GB of memory at Q4_K (a 4.1 GB file) with an 8K context window, so it fits on a 12 GB GPU.

LLaVA is a 6.74B-parameter LLaVA model in GGUF format, quantized by HyperMink. Its trained context length is 4K tokens. The repository has 1 quant file, from 4.1 GB (Q4_K) to 4.1 GB (Q4_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K4.1 GB 6.7 GB
Fits Get file →

What GPU do you need for 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 Q4_K (4.1 GB file, about 8.9 GB in use).

Which LLaVA quant should you choose?

Q4_K (4.1 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

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 byHyperMink
FamilyLLaVA
RepositoryHyperMink/LLaVA
Licensellama2
Downloads (HF)4
Last updated2024-05-22

Frequently asked questions about LLaVA

How much VRAM does LLaVA need?

About 8.9 GB at Q4_K 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 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 LLaVA GGUF?

It depends on the quant: Q4_K is 4.1 GB.

What context length does 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 LLaVA GGUF?

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

What license does LLaVA use?

Hugging Face lists the license as llama2. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Similar models

Browse all →

More from HyperMink

All by HyperMink →

More LLaVA models

All LLaVA →

Other small models

All small models →