LL

ggml llava v1.5 7b

LLaVAGGUF by benjaminchamUpdated 2023-12-28
Download on Hugging Face
Parameters6.74B
Context4K
Layers32
Architecturellama
Smallest quant4.1 GB
Quick answer

ggml llava v1.5 7b 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. This repository has 2 quants, from 4.1 GB (Q4_K) to 4.8 GB (Q5_K).

ggml llava v1.5 7b is a 6.74B-parameter LLaVA model in GGUF format, quantized by benjamincham. Its trained context length is 4K tokens. The repository has 2 quant files, from 4.1 GB (Q4_K) to 4.8 GB (Q5_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K4.1 GB 6.7 GB
Fits Get file →
Q5_K4.8 GB 7.4 GB
Tight Get file →

What GPU do you need for ggml llava v1.5 7b?

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 Q5_K (4.8 GB file, about 9.6 GB in use).

Which ggml llava v1.5 7b 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 bybenjamincham
FamilyLLaVA
Downloads (HF)24
Last updated2023-12-28

Frequently asked questions about ggml llava v1.5 7b

How much VRAM does ggml llava v1.5 7b 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 ggml llava v1.5 7b 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 ggml llava v1.5 7b GGUF?

It depends on the quant: Q4_K is 4.1 GB, Q5_K is 4.8 GB.

What context length does ggml llava v1.5 7b 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 ggml llava v1.5 7b GGUF?

The files are on Hugging Face in the benjamincham/ggml_llava-v1.5-7b 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 benjamincham

All by benjamincham →

More LLaVA models

All LLaVA →

Other small models

All small models →