SH

ShareGPT4V 13B quant

SharegptGGUF by cmp-nctUpdated 2024-01-26
Download on Hugging Face
Parameters13B
Context4K
Layers40
Architecturellama
Smallest quant5.7 GB
Quick answer

ShareGPT4V 13B quant needs about 12.9 GB of memory at Q3_K_S (a 5.7 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 2 quants, from 5.7 GB (Q3_K_S) to 7.9 GB (Q4_K).

ShareGPT4V 13B quant is a 13B-parameter Sharegpt model in GGUF format, quantized by cmp-nct. Its trained context length is 4K tokens. The repository has 2 quant files, from 5.7 GB (Q3_K_S) to 7.9 GB (Q4_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_S5.7 GB 9.5 GB
Too big Get file →
Q4_K7.9 GB 11.7 GB
Too big Get file →

What GPU do you need for ShareGPT4V 13B quant?

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: the best quant that fits is Q4_K (7.9 GB file, about 15.1 GB in use).

Which ShareGPT4V 13B quant quant should you choose?

Q3_K_S (5.7 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters13B
Layers40
Trained context4,096 tokens
KV cache (fp16)800 KB per token

Source

Quantized bycmp-nct
FamilySharegpt
Licensellama2
Downloads (HF)71
Last updated2024-01-26

Frequently asked questions about ShareGPT4V 13B quant

How much VRAM does ShareGPT4V 13B quant need?

About 12.9 GB at Q3_K_S with an 8K context window. That is the 5.7 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 ShareGPT4V 13B quant on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 12.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of ShareGPT4V 13B quant GGUF?

It depends on the quant: Q3_K_S is 5.7 GB, Q4_K is 7.9 GB.

What context length does ShareGPT4V 13B quant support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 6.7 GB at 8K and 3.4 GB at 4K.

Where can I download ShareGPT4V 13B quant GGUF?

The files are on Hugging Face in the cmp-nct/ShareGPT4V-13B-quant-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does ShareGPT4V 13B quant 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 cmp-nct

All by cmp-nct →

More Sharegpt models

All Sharegpt →

Other medium models

All medium models →