LL

Meta Llama 3.1 8b Bnb 4bit

LlamaGGUF by Tlent21Updated 2024-08-18
Download on Hugging Face
Parameters8.03B
Context128K
Layers32
Architecturellama
Smallest quant16.1 GB
Quick answer

Meta Llama 3.1 8b Bnb 4bit needs about 17.6 GB of memory at F16 (a 16.1 GB file) with an 8K context window, so it fits on a 24 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Meta Llama 3.1 8b Bnb 4bit is a 8.03B-parameter Llama model in GGUF format, quantized by Tlent21. Its trained context length is 128K tokens. The repository has 1 quant file, from 16.1 GB (F16) to 16.1 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F1616.1 GB 17.6 GB
Too big Get file →

What GPU do you need for Meta Llama 3.1 8b Bnb 4bit?

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: no quant fits at an 8K context.
  • 24 GB VRAM: the best quant that fits is F16 (16.1 GB file, about 17.6 GB in use).

Which Meta Llama 3.1 8b Bnb 4bit quant should you choose?

F16 (16.1 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

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 byTlent21
FamilyLlama
RepositoryTlent21/Llama
Downloads (HF)4
Last updated2024-08-18

Frequently asked questions about Meta Llama 3.1 8b Bnb 4bit

How much VRAM does Meta Llama 3.1 8b Bnb 4bit need?

About 17.6 GB at F16 with an 8K context window. That is the 16.1 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 Meta Llama 3.1 8b Bnb 4bit on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 17.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Meta Llama 3.1 8b Bnb 4bit GGUF?

It depends on the quant: F16 is 16.1 GB.

What context length does Meta Llama 3.1 8b Bnb 4bit 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 Meta Llama 3.1 8b Bnb 4bit GGUF?

The files are on Hugging Face in the Tlent21/Llama 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 Llama models

All Llama →

Other small models

All small models →