LL

llava test

LLaVAGGUF by ha1772007Updated 2024-08-14
Download on Hugging Face
Parameters3.82B
Context4K
Layers32
Architecturellama
Smallest quant1.4 GB
Quick answer

llava test needs about 5.2 GB of memory at F16 (a 1.4 GB file) with an 8K context window, so it fits on a 6 GB GPU.

llava test is a 3.82B-parameter LLaVA model in GGUF format, quantized by ha1772007. Its trained context length is 4K tokens. The repository has 1 quant file, from 1.4 GB (F16) to 1.4 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F161.4 GB 3.6 GB
Fits Get file →

What GPU do you need for llava test?

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: the best quant that fits is F16 (1.4 GB file, about 5.2 GB in use).

Which llava test quant should you choose?

F16 (1.4 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
Parameters3.82B
Layers32
Trained context4,096 tokens
KV cache (fp16)384 KB per token

Source

Quantized byha1772007
FamilyLLaVA
Downloads (HF)6
Last updated2024-08-14

Frequently asked questions about llava test

How much VRAM does llava test need?

About 5.2 GB at F16 with an 8K context window. That is the 1.4 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 llava test on an 8 GB GPU?

Yes, with F16: the 1.4 GB file needs about 5.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of llava test GGUF?

It depends on the quant: F16 is 1.4 GB.

What context length does llava test support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 3.2 GB at 8K and 1.6 GB at 4K.

Where can I download llava test GGUF?

The files are on Hugging Face in the ha1772007/llava-test 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 ha1772007

All by ha1772007 →

More LLaVA models

All LLaVA →

Other small models

All small models →