LL

llava v1.6 vicuna 13b

LLaVAGGUF by cjpaisUpdated 2024-03-07
Download on Hugging Face
Parameters13B
Context4K
Layers40
Architecturellama
Smallest quant5.3 GB
Quick answer

llava v1.6 vicuna 13b needs about 15.1 GB of memory at Q4_K_M (a 7.9 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 7 quants, from 5.3 GB (Q3_K_XS) to 13.8 GB (Q8_0).

LLaVA 1.6 Vicuna 13B – multimodal LLM with vision support

LLaVA 1.6 Vicuna 13B is a 13‑billion‑parameter multimodal model that combines a Vicuna 13B base with vision capabilities. It is trained on 558K image‑text pairs and 158K instruction‑following examples. The model is released under the Apache‑2.0 license.

Good at

  • Vision‑enabled instruction following
  • Multimodal chat
  • Research on LMMs

Limits

  • No vision support in older quants
  • Large VRAM requirement for high‑quality quants
  • No audio or video processing

Best for

  • Research prototyping
  • Multimodal chatbot demos
  • Vision‑based Q&A

Who it’s for. Researchers, hobbyists, and developers working on multimodal language models and chatbots. The model is suitable for those who need a vision‑enabled LLM for experimentation and prototyping.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_XS5.3 GB 9.2 GB
Too big Get file →
Q3_K_M6.3 GB 10.2 GB
Too big Get file →
Q4_K_M7.9 GB 11.7 GB
Too big Get file →
Q5_K_S9.0 GB 12.8 GB
Too big Get file →
Q5_K_M9.2 GB 13.1 GB
Too big Get file →
Q6_K10.7 GB 14.5 GB
Too big Get file →
Q8_013.8 GB 17.7 GB
Too big Get file →

For 8 GB VRAM, use Q3_K_XS (5.31 GB, 12.5 GB memory at 8 k context). For 12 GB VRAM, Q4_K_M (7.87 GB, 15.1 GB memory) is a good balance. If 16 GB VRAM is available, Q5_K_M (9.23 GB, 16.4 GB memory) offers higher quality.

What GPU do you need for llava v1.6 vicuna 13b?

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_M (7.9 GB file, about 15.1 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (13.8 GB file, about 21.0 GB in use).

Which llava v1.6 vicuna 13b quant should you choose?

Q4_K_M is the usual starting point for llava v1.6 vicuna 13b: it balances file size and quality well. Here it is a 7.9 GB file.

The Q8_0 file is 13.8 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q3_K_XS at 5.3 GB, with the quality trade-offs that come with fewer bits. 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 bycjpais
FamilyLLaVA
Licenseapache-2.0
Downloads (HF)1,172
Last updated2024-03-07

Frequently asked questions about llava v1.6 vicuna 13b

How much VRAM does llava v1.6 vicuna 13b need?

About 15.1 GB at Q4_K_M with an 8K context window. That is the 7.9 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 v1.6 vicuna 13b on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 12.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of llava v1.6 vicuna 13b GGUF?

It depends on the quant: Q3_K_XS is 5.3 GB, Q3_K_M is 6.3 GB, Q4_K_M is 7.9 GB, Q5_K_S is 9.0 GB, Q5_K_M is 9.2 GB, Q6_K is 10.7 GB and 1 more.

What context length does llava v1.6 vicuna 13b 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 llava v1.6 vicuna 13b GGUF?

The files are on Hugging Face in the cjpais/llava-v1.6-vicuna-13b-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 llava v1.6 vicuna 13b use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run LLaVA 1.6 Vicuna 13B on 8 GB VRAM?

Yes, the Q3_K_XS quant uses 5.31 GB and requires about 12.5 GB of VRAM at 8 k context.

Does this model support vision tasks?

Yes, it includes vision capabilities and is trained on image‑text pairs.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Similar models

Browse all →

More from cjpais

All by cjpais →

More LLaVA models

All LLaVA →

Other medium models

All medium models →