LL

liuhaotian llava v1.5 13b

LLaVAGGUF by PsiPiUpdated 2024-03-11
Download on Hugging Face
Parameters13B
Context4K
Layers40
Architecturellama
Smallest quant5.4 GB
Quick answer

liuhaotian llava v1.5 13b needs about 16.4 GB of memory at Q5_K_M (a 9.2 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 6 quants, from 5.4 GB (Q2_K) to 26.0 GB (F16).

LLaVA v1.5 13B – multimodal LLM with vision capability

LLaVA v1.5 13B is a 13‑billion parameter multimodal model fine‑tuned on LLaMA/Vicuna. It supports image input and instruction following. The model is available in multiple GGUF quantizations for llama.cpp inference.

Good at

  • Vision‑enabled text generation
  • Multimodal instruction following
  • Research‑grade LMM

Limits

  • No vision support in non‑quantized variants
  • Requires 8‑k context for estimates
  • License not specified

Best for

  • Research on multimodal chatbots
  • Hobbyist experimentation
  • Vision‑augmented text tasks

Who it’s for. Researchers and hobbyists in computer vision, NLP, and AI who need a multimodal LLM for experimentation and prototyping.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K5.4 GB 9.3 GB
Too big Get file →
Q4_07.4 GB 11.2 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 →
F1626.0 GB 29.9 GB
Too big Get file →

For 8‑GB VRAM, Q2_K (5.43 GB, 12.6 GB memory) or Q4_0 (7.37 GB, 14.6 GB memory) are suitable. For 16‑GB VRAM, Q5_K_M (9.23 GB, 16.4 GB memory) or Q6_K (10.68 GB, 17.9 GB memory) work well. Larger models need more VRAM.

What GPU do you need for liuhaotian llava v1.5 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_0 (7.4 GB file, about 14.6 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (13.8 GB file, about 21.0 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (13.8 GB file, about 21.0 GB in use).
  • 48 GB VRAM: the best quant that fits is F16 (26.0 GB file, about 33.2 GB in use).

Which liuhaotian llava v1.5 13b quant should you choose?

Q5_K_M (9.2 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

If memory is tight, the smallest file is Q2_K at 5.4 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

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 byPsiPi
FamilyLLaVA
Downloads (HF)1,166
Last updated2024-03-11

Frequently asked questions about liuhaotian llava v1.5 13b

How much VRAM does liuhaotian llava v1.5 13b need?

About 16.4 GB at Q5_K_M with an 8K context window. That is the 9.2 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 liuhaotian llava v1.5 13b on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 12.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of liuhaotian llava v1.5 13b GGUF?

It depends on the quant: Q2_K is 5.4 GB, Q4_0 is 7.4 GB, Q5_K_M is 9.2 GB, Q6_K is 10.7 GB, Q8_0 is 13.8 GB, F16 is 26.0 GB.

What context length does liuhaotian llava v1.5 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 liuhaotian llava v1.5 13b GGUF?

The files are on Hugging Face in the PsiPi/liuhaotian_llava-v1.5-13b-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run LLaVA v1.5 13B on 8 GB VRAM?

Yes, using Q2_K or Q4_0 quantizations will fit within 8 GB VRAM with approximate memory usage of 12.6 GB and 14.6 GB respectively.

Does this model support vision tasks?

Yes, the model has detected vision ability and can process images as input.

What is the context length of this model?

The trained context length is 4096 tokens.

Similar models

Browse all →

More from PsiPi

All by PsiPi →

More LLaVA models

All LLaVA →

Other medium models

All medium models →