LL

llava-llama-3-8b-v1_1

LlamaGGUF by djward888Updated 2024-04-22
Download on Hugging Face
Parameters8.03B
Context8K
Layers32
Architecturellama
Smallest quant5.6 GB
Quick answer

llava-llama-3-8b-v1_1 needs about 7.2 GB of memory at Q5_0 (a 5.6 GB file) with an 8K context window, so it fits on a 8 GB GPU.

llava-llama-3-8b-v1_1 is a 8.03B-parameter Llama model in GGUF format, quantized by djward888. Its trained context length is 8K tokens. The repository has 1 quant file, from 5.6 GB (Q5_0) to 5.6 GB (Q5_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_05.6 GB 7.2 GB
Fits Get file →

What GPU do you need for llava-llama-3-8b-v1_1?

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: the best quant that fits is Q5_0 (5.6 GB file, about 7.2 GB in use).

Which llava-llama-3-8b-v1_1 quant should you choose?

Q5_0 (5.6 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.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters8.03B
Layers32
Trained context8,192 tokens
KV cache (fp16)128 KB per token

Source

Quantized bydjward888
FamilyLlama
Downloads (HF)38
Last updated2024-04-22

Frequently asked questions about llava-llama-3-8b-v1_1

How much VRAM does llava-llama-3-8b-v1_1 need?

About 7.2 GB at Q5_0 with an 8K context window. That is the 5.6 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-llama-3-8b-v1_1 on an 8 GB GPU?

Yes, with Q5_0: the 5.6 GB file needs about 7.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of llava-llama-3-8b-v1_1 GGUF?

It depends on the quant: Q5_0 is 5.6 GB.

What context length does llava-llama-3-8b-v1_1 support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 1.1 GB at 8K and 1.1 GB at 8K.

Where can I download llava-llama-3-8b-v1_1 GGUF?

The files are on Hugging Face in the djward888/llava-llama-3-8b-v1_1-Q5_0-GGUF 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 djward888

All by djward888 →

More Llama models

All Llama →

Other small models

All small models →