LL

Meta-Llama-3-120B-Instruct

LlamaGGUF by LiteLLMsUpdated 2024-05-30
Download on Hugging Face
Parameters120B
Context8K
Layers140
Architecturellama
Smallest quant52.8 GB
Quick answer

Meta-Llama-3-120B-Instruct needs about 78.4 GB of memory at Q4_K_M (a 73.2 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 14 quants, from 52.8 GB (Q3_K_S) to 129.5 GB (Q8_0).

Meta-Llama-3-120B-Instruct is a 120B-parameter Llama model in GGUF format, quantized by LiteLLMs. Its trained context length is 8K tokens. The repository has 14 quant files, from 52.8 GB (Q3_K_S) to 129.5 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_S52.8 GB (4 parts) 58.0 GB
Too big Get file →
Q3_K_M58.8 GB (4 parts) 64.0 GB
Too big Get file →
Q3_K_L64.0 GB (4 parts) 69.2 GB
Too big Get file →
Q2_K67.6 GB (4 parts) 72.8 GB
Too big Get file →
Q4_068.9 GB (5 parts) 74.0 GB
Too big Get file →
Q4_K_S69.4 GB (5 parts) 74.6 GB
Too big Get file →
Q4_K_M73.2 GB (5 parts) 78.4 GB
Too big Get file →
Q4_176.4 GB (5 parts) 81.6 GB
Too big Get file →
Q5_084.0 GB (5 parts) 89.2 GB
Too big Get file →
Q5_K_S84.0 GB (5 parts) 89.2 GB
Too big Get file →
Q5_K_M86.2 GB (6 parts) 91.4 GB
Too big Get file →
Q5_191.5 GB (6 parts) 96.7 GB
Too big Get file →
Q6_K100.0 GB (6 parts) 105.2 GB
Too big Get file →
Q8_0129.5 GB (8 parts) 134.7 GB
Too big Get file →

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

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 quant should you choose?

Q4_K_M is the usual starting point for Meta-Llama-3-120B-Instruct: it balances file size and quality well. Here it is a 73.2 GB file.

The Q8_0 file is 129.5 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q3_K_S at 52.8 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters120B
Layers140
Trained context8,192 tokens
KV cache (fp16)560 KB per token

Source

Quantized byLiteLLMs
FamilyLlama
Licenseother
Downloads (HF)72
Last updated2024-05-30

Frequently asked questions about Meta-Llama-3-120B-Instruct

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

About 78.4 GB at Q4_K_M with an 8K context window. That is the 73.2 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 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 58.0 GB, so you would need a larger GPU or CPU offloading.

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

It depends on the quant: Q3_K_S is 52.8 GB, Q3_K_M is 58.8 GB, Q3_K_L is 64.0 GB, Q2_K is 67.6 GB, Q4_0 is 68.9 GB, Q4_K_S is 69.4 GB and 8 more.

What context length does Meta-Llama-3-120B-Instruct 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 GGUF?

The files are on Hugging Face in the LiteLLMs/Meta-Llama-3-120B-Instruct-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Meta-Llama-3-120B-Instruct use?

Hugging Face lists the license as other. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Other GGUFs of Meta-Llama-3-70B-Instruct

Similar models

Browse all →

More from LiteLLMs

All by LiteLLMs →

More Llama models

All Llama →

Other large models

All large models →