LL

Meta Llama 3 120B Instruct merged

LlamaGGUF by imi2Updated 2024-04-22
Download on Hugging Face
Parameters122B
Context8K
Layers140
Architecturellama
Smallest quant65.9 GB
Quick answer

Meta Llama 3 120B Instruct merged needs about 71.1 GB of memory at IQ4_XS (a 65.9 GB file) with an 8K context window, which is more than a 48 GB GPU holds.

Meta Llama 3 120B Instruct merged is a 122B-parameter Llama model in GGUF format, quantized by imi2. Its trained context length is 8K tokens. The repository has 1 quant file, from 65.9 GB (IQ4_XS) to 65.9 GB (IQ4_XS).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ4_XS65.9 GB (10 parts) 71.1 GB
Too big Get file →

What GPU do you need for Meta Llama 3 120B Instruct merged?

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 Meta Llama 3 120B Instruct merged quant should you choose?

IQ4_XS (65.9 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters122B
Layers140
Trained context8,192 tokens
KV cache (fp16)560 KB per token

Source

Quantized byimi2
FamilyLlama
Downloads (HF)21
Last updated2024-04-22

Frequently asked questions about Meta Llama 3 120B Instruct merged

How much VRAM does Meta Llama 3 120B Instruct merged need?

About 71.1 GB at IQ4_XS with an 8K context window. That is the 65.9 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 Meta Llama 3 120B Instruct merged on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 71.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Meta Llama 3 120B Instruct merged GGUF?

It depends on the quant: IQ4_XS is 65.9 GB.

What context length does Meta Llama 3 120B Instruct merged support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 4.7 GB at 8K and 4.7 GB at 8K.

Where can I download Meta Llama 3 120B Instruct merged GGUF?

The files are on Hugging Face in the imi2/Meta-Llama-3-120B-Instruct-merged-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 imi2

All by imi2 →

More Llama models

All Llama →

Other large models

All large models →