LL

Meta llama_Meta Llama 3 70B Instruct

LlamaGGUF by ThomasBaruzierUpdated 2024-08-23
Download on Hugging Face
Parameters70.6B
Context8K
Layers80
Architecturellama
Smallest quant15.3 GB
Quick answer

Meta llama_Meta Llama 3 70B Instruct 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 31 quants, from 15.3 GB (IQ1_S) to 141.1 GB (F16).

Meta Llama 3 70B Instruct – 70 billion‑parameter instruction‑tuned LLM

Meta Llama 3 70B Instruct is a 70 billion‑parameter, 8 k context length model tuned for dialogue. It is available in multiple GGUF quantizations from IQ1_S to F16. The model is licensed under the llama3 license and supports text and code generation only.

Good at

  • Dialogue generation
  • Instruction following
  • Large‑scale text synthesis

Limits

  • No vision support
  • Requires 8 k context for full capability
  • License is llama3

Best for

  • Chatbot development
  • Content drafting
  • Code assistance

Who it’s for. Developers and researchers needing a large instruction‑tuned model for text‑only applications. The model is suitable for environments that can accommodate its memory footprint and comply with the llama3 license.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S15.3 GB 18.5 GB
Too big Get file →
IQ1_M16.8 GB 19.9 GB
Too big Get file →
IQ2_XXS19.1 GB 22.3 GB
Too big Get file →
IQ2_XS21.1 GB 24.3 GB
Too big Get file →
IQ2_S22.2 GB 25.4 GB
Too big Get file →
IQ2_M24.1 GB 27.3 GB
Too big Get file →
Q2_K_S24.5 GB 27.7 GB
Too big Get file →
Q2_K26.4 GB 29.6 GB
Too big Get file →
IQ3_XXS27.5 GB 30.7 GB
Too big Get file →
IQ3_XS29.3 GB 32.5 GB
Too big Get file →
IQ3_S30.9 GB 34.1 GB
Too big Get file →
Q3_K_S30.9 GB 34.1 GB
Too big Get file →
IQ3_M31.9 GB 35.1 GB
Too big Get file →
Q3_K_M34.3 GB 37.5 GB
Too big Get file →
Q3_K_L37.1 GB 40.3 GB
Too big Get file →
IQ4_XS37.9 GB 41.1 GB
Too big Get file →
Q4_040.0 GB 43.2 GB
Too big Get file →
Q4_040.0 GB 43.2 GB
Too big Get file →
Q4_040.0 GB 43.2 GB
Too big Get file →
IQ4_NL40.1 GB 43.2 GB
Too big Get file →
Q4_040.1 GB 43.3 GB
Too big Get file →
Q4_K_S40.3 GB 43.5 GB
Too big Get file →
Q4_K_M42.5 GB 45.7 GB
Too big Get file →
Q4_144.3 GB 47.5 GB
Too big Get file →
Q5_K_S48.7 GB 51.8 GB
Too big Get file →
Q5_048.8 GB 52.0 GB
Too big Get file →
Q5_K_M49.9 GB 53.1 GB
Too big Get file →
Q5_153.0 GB (2 parts) 56.2 GB
Too big Get file →
Q6_K57.9 GB (2 parts) 61.1 GB
Too big Get file →
Q8_075.0 GB (2 parts) 78.2 GB
Too big Get file →
F16141.1 GB (3 parts) 144.3 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (15.34 GB file, ~18.5 GB VRAM). For 16 GB VRAM, IQ2_S (22.24 GB file, ~25.4 GB VRAM). For 24 GB VRAM, Q4_K_M (42.52 GB file, ~45.7 GB VRAM). Estimates are approximate.

What GPU do you need for Meta llama_Meta Llama 3 70B 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: the best quant that fits is IQ2_XXS (19.1 GB file, about 22.3 GB in use).
  • 32 GB VRAM: the best quant that fits is IQ3_XXS (27.5 GB file, about 30.7 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_Meta Llama 3 70B Instruct quant should you choose?

Q4_K_M is the usual starting point for Meta llama_Meta Llama 3 70B Instruct: 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 IQ1_S at 15.3 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 byThomasBaruzier
FamilyLlama
Licensellama3
Downloads (HF)13,474
Last updated2024-08-23

Frequently asked questions about Meta llama_Meta Llama 3 70B Instruct

How much VRAM does Meta llama_Meta Llama 3 70B Instruct 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_Meta Llama 3 70B Instruct on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 18.5 GB, so you would need a larger GPU or CPU offloading.

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

It depends on the quant: IQ1_S is 15.3 GB, IQ1_M is 16.8 GB, IQ2_XXS is 19.1 GB, IQ2_XS is 21.1 GB, IQ2_S is 22.2 GB, IQ2_M is 24.1 GB and 25 more.

What context length does Meta llama_Meta Llama 3 70B 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 2.7 GB at 8K and 2.7 GB at 8K.

Where can I download Meta llama_Meta Llama 3 70B Instruct GGUF?

The files are on Hugging Face in the ThomasBaruzier/Meta-Llama-3-70B-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_Meta Llama 3 70B Instruct 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.

Can I run Meta Llama 3 70B Instruct on 8 GB VRAM?

Use the IQ1_S quantization; it requires about 18.5 GB VRAM at 8 k context, so 8 GB VRAM is insufficient.

Does this model support image input?

No, the model accepts text only and generates text or code.

What license applies to this model?

The model is released under the llama3 license, with a custom commercial license available at the Meta website.

Similar models

Browse all →

More from ThomasBaruzier

All by ThomasBaruzier →

More Llama models

All Llama →

Other large models

All large models →