LL

Llama 3 70Bx2 MOE

LlamaGGUF by cloudyuUpdated 2024-05-20
Download on Hugging Face
Parameters127B
Context8K
Layers80
Architecturellama
Smallest quant90.0 GB
Quick answer

Llama 3 70Bx2 MOE needs about 93.1 GB of memory at Q5_K (a 90.0 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 2 quants, from 90.0 GB (Q5_K) to 134.9 GB (Q8_0).

Llama 3 70Bx2 MOE is a 127B-parameter Llama model in GGUF format, quantized by cloudyu. Its trained context length is 8K tokens. The repository has 2 quant files, from 90.0 GB (Q5_K) to 134.9 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K90.0 GB (2 parts) 93.1 GB
Too big Get file →
Q8_0134.9 GB (4 parts) 138.1 GB
Too big Get file →

What GPU do you need for Llama 3 70Bx2 MOE?

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.

Which Llama 3 70Bx2 MOE quant should you choose?

Q5_K (90.0 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
Parameters127B (approximate, mixture of experts)
Layers80
Trained context8,192 tokens
KV cache (fp16)320 KB per token

Source

Quantized bycloudyu
FamilyLlama
Downloads (HF)8
Last updated2024-05-20

Frequently asked questions about Llama 3 70Bx2 MOE

How much VRAM does Llama 3 70Bx2 MOE need?

About 93.1 GB at Q5_K with an 8K context window. That is the 90.0 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 70Bx2 MOE on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 93.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Llama 3 70Bx2 MOE GGUF?

It depends on the quant: Q5_K is 90.0 GB, Q8_0 is 134.9 GB.

What context length does Llama 3 70Bx2 MOE support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 2.7 GB at 8K and 2.7 GB at 8K.

Where can I download Llama 3 70Bx2 MOE GGUF?

The files are on Hugging Face in the cloudyu/Llama-3-70Bx2-MOE-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 cloudyu

All by cloudyu →

More Llama models

All Llama →

Other large models

All large models →