LL

Meta-Llama-3-70B

LlamaGGUF by LiteLLMsUpdated 2024-05-30
Download on Hugging Face
Parameters70.6B
Context8K
Layers80
Architecturellama
Smallest quant26.4 GB
Quick answer

Meta-Llama-3-70B needs about 45.7 GB of memory at Q4_K_M (a 42.5 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 14 quants, from 26.4 GB (Q2_K) to 75.0 GB (Q8_0).

Meta-Llama-3-70B is a 70.6B-parameter Llama model in GGUF format, quantized by LiteLLMs. Its trained context length is 8K tokens. The repository has 14 quant files, from 26.4 GB (Q2_K) to 75.0 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K26.4 GB (2 parts) 29.6 GB
Too big Get file →
Q3_K_S30.9 GB (2 parts) 34.1 GB
Too big Get file →
Q3_K_M34.3 GB (2 parts) 37.5 GB
Too big Get file →
Q3_K_L37.1 GB (3 parts) 40.3 GB
Too big Get file →
Q4_040.0 GB (3 parts) 43.2 GB
Too big Get file →
Q4_K_S40.3 GB (3 parts) 43.5 GB
Too big Get file →
Q4_K_M42.5 GB (3 parts) 45.7 GB
Too big Get file →
Q4_144.3 GB (3 parts) 47.5 GB
Too big Get file →
Q5_048.7 GB (3 parts) 51.8 GB
Too big Get file →
Q5_K_S48.7 GB (3 parts) 51.8 GB
Too big Get file →
Q5_K_M49.9 GB (3 parts) 53.1 GB
Too big Get file →
Q5_153.0 GB (4 parts) 56.2 GB
Too big Get file →
Q6_K57.9 GB (4 parts) 61.1 GB
Too big Get file →
Q8_075.0 GB (5 parts) 78.2 GB
Too big Get file →

What GPU do you need for Meta-Llama-3-70B?

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: the best quant that fits is Q2_K (26.4 GB file, about 29.6 GB in use).
  • 48 GB VRAM: the best quant that fits is Q4_1 (44.3 GB file, about 47.5 GB in use).

Which Meta-Llama-3-70B quant should you choose?

Q4_K_M is the usual starting point for Meta-Llama-3-70B: it balances file size and quality well. Here it is a 42.5 GB file.

The Q8_0 file is 75.0 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 Q2_K at 26.4 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters70.6B
Layers80
Trained context8,192 tokens
KV cache (fp16)320 KB per token

Source

Quantized byLiteLLMs
FamilyLlama
Licensellama3
Downloads (HF)54
Last updated2024-05-30

Frequently asked questions about Meta-Llama-3-70B

How much VRAM does Meta-Llama-3-70B need?

About 45.7 GB at Q4_K_M with an 8K context window. That is the 42.5 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-3-70B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 29.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Meta-Llama-3-70B GGUF?

It depends on the quant: Q2_K is 26.4 GB, Q3_K_S is 30.9 GB, Q3_K_M is 34.3 GB, Q3_K_L is 37.1 GB, Q4_0 is 40.0 GB, Q4_K_S is 40.3 GB and 8 more.

What context length does Meta-Llama-3-70B 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 Meta-Llama-3-70B GGUF?

The files are on Hugging Face in the LiteLLMs/Meta-Llama-3-70B-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-3-70B use?

Hugging Face lists the license as llama3. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Similar models

Browse all →

More from LiteLLMs

All by LiteLLMs →

More Llama models

All Llama →

Other large models

All large models →