LL

llama3 8x8 q 8

LlamaGGUF by kloodiaUpdated 2024-05-02
Download on Hugging Face
Parameters58.8B
Context8K
Layers32
Architecturellama
Smallest quant62.4 GB
Quick answer

llama3 8x8 q 8 needs about 64.0 GB of memory at its main file (a 62.4 GB file) with an 8K context window, which is more than a 48 GB GPU holds.

llama3 8x8 q 8 is a 58.8B-parameter Llama model in GGUF format, quantized by kloodia. Its trained context length is 8K tokens. The repository has 1 quant file, from 62.4 GB to 62.4 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—62.4 GB (13 parts) 64.0 GB
Too big Get file →

What GPU do you need for llama3 8x8 q 8?

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: no quant fits at an 8K context.
  • 32 GB VRAM: no quant fits at an 8K context.
  • 48 GB VRAM: no quant fits at an 8K context.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters58.8B (approximate, mixture of experts)
Layers32
Trained context8,192 tokens
KV cache (fp16)128 KB per token

Source

Quantized bykloodia
FamilyLlama
Downloads (HF)36
Last updated2024-05-02

Frequently asked questions about llama3 8x8 q 8

How much VRAM does llama3 8x8 q 8 need?

About 64.0 GB at its main file with an 8K context window. That is the 62.4 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 llama3 8x8 q 8 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 64.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of llama3 8x8 q 8 GGUF?

It depends on the quant: file is 62.4 GB.

What context length does llama3 8x8 q 8 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 llama3 8x8 q 8 GGUF?

The files are on Hugging Face in the kloodia/llama3-8x8-q_8 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 kloodia

All by kloodia →

More Llama models

All Llama →

Other large models

All large models →