LL

Llama 3.1 4bit convrsation

LlamaGGUF by vignesh-spericornUpdated 2024-07-29
Download on Hugging Face
Parameters8.03B
Context128K
Layers32
Architecturellama
Smallest quant4.9 GB
Quick answer

Llama 3.1 4bit convrsation 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 16.1 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Llama 3.1 4bit convrsation is a 8.03B-parameter Llama model in GGUF format, quantized by vignesh-spericorn. Its trained context length is 128K tokens. The repository has 2 quant files, from 4.9 GB (Q4_K_M) to 16.1 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M4.9 GB 6.5 GB
Fits Get file →
F1616.1 GB 17.6 GB
Too big Get file →

What GPU do you need for Llama 3.1 4bit convrsation?

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 Q4_K_M (4.9 GB file, about 6.5 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_K_M (4.9 GB file, about 6.5 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (16.1 GB file, about 17.6 GB in use).

Which Llama 3.1 4bit convrsation quant should you choose?

Q4_K_M is the usual starting point for Llama 3.1 4bit convrsation: it balances file size and quality well. Here it is a 4.9 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters8.03B
Layers32
Trained context131,072 tokens
KV cache (fp16)128 KB per token

Source

Quantized byvignesh-spericorn
FamilyLlama
Licenseapache-2.0
Downloads (HF)40
Last updated2024-07-29

Frequently asked questions about Llama 3.1 4bit convrsation

How much VRAM does Llama 3.1 4bit convrsation 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 Llama 3.1 4bit convrsation 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 Llama 3.1 4bit convrsation GGUF?

It depends on the quant: Q4_K_M is 4.9 GB, F16 is 16.1 GB.

What context length does Llama 3.1 4bit convrsation support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download Llama 3.1 4bit convrsation GGUF?

The files are on Hugging Face in the vignesh-spericorn/Llama-3.1-4bit-convrsation repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Llama 3.1 4bit convrsation 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 vignesh-spericorn

All by vignesh-spericorn →

More Llama models

All Llama →

Other small models

All small models →