LL

WiNGPT2 Llama 3 8B Chat

LlamaGGUF by winninghealthUpdated 2024-04-25
Download on Hugging Face
Parameters8.03B
Context8K
Layers32
Architecturellama
Smallest quant4.9 GB
Quick answer

WiNGPT2 Llama 3 8B Chat needs about 6.5 GB of memory at Q4_K_M (a 4.9 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 2 quants, from 4.9 GB (Q4_K_M) to 8.5 GB (Q8_0).

WiNGPT2 Llama 3 8B Chat is a 8.03B-parameter Llama model in GGUF format, quantized by winninghealth. Its trained context length is 8K tokens. The repository has 2 quant files, from 4.9 GB (Q4_K_M) to 8.5 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M4.9 GB 6.5 GB
Fits Get file →
Q8_08.5 GB 10.1 GB
Too big Get file →

What GPU do you need for WiNGPT2 Llama 3 8B Chat?

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 Q4_K_M (4.9 GB file, about 6.5 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (8.5 GB file, about 10.1 GB in use).

Which WiNGPT2 Llama 3 8B Chat quant should you choose?

Q4_K_M is the usual starting point for WiNGPT2 Llama 3 8B Chat: it balances file size and quality well. Here it is a 4.9 GB file.

The Q8_0 file is 8.5 GB, about 1.7 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.

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 bywinninghealth
FamilyLlama
Licenseapache-2.0
Downloads (HF)52
Last updated2024-04-25

Frequently asked questions about WiNGPT2 Llama 3 8B Chat

How much VRAM does WiNGPT2 Llama 3 8B Chat need?

About 6.5 GB at Q4_K_M with an 8K context window. That is the 4.9 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 WiNGPT2 Llama 3 8B Chat on an 8 GB GPU?

Yes, with Q4_K_M: the 4.9 GB file needs about 6.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of WiNGPT2 Llama 3 8B Chat GGUF?

It depends on the quant: Q4_K_M is 4.9 GB, Q8_0 is 8.5 GB.

What context length does WiNGPT2 Llama 3 8B Chat 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 WiNGPT2 Llama 3 8B Chat GGUF?

The files are on Hugging Face in the winninghealth/WiNGPT2-Llama-3-8B-Chat-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 WiNGPT2 Llama 3 8B Chat 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.

Similar models

Browse all →

More from winninghealth

All by winninghealth →

More Llama models

All Llama →

Other small models

All small models →