LL

Meta-Llama-3-70B-Instruct

LlamaGGUF by RichardErkhovUpdated 2024-04-28
Download on Hugging Face
Parameters70.6B
Context8K
Layers80
Architecturellama
Smallest quant26.4 GB
Quick answer

Meta-Llama-3-70B-Instruct needs about 35.1 GB of memory at IQ3_M (a 31.9 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 9 quants, from 26.4 GB (Q2_K) to 38.3 GB (IQ4_XS).

Meta-Llama-3-70B-Instruct is a 70.6B-parameter Llama model in GGUF format, quantized by RichardErkhov. Its trained context length is 8K tokens. The repository has 9 quant files, from 26.4 GB (Q2_K) to 38.3 GB (IQ4_XS).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K26.4 GB 29.6 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_K34.3 GB 37.5 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_XS38.3 GB 41.5 GB
Too big Get file →

What GPU do you need for 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: 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 IQ4_XS (38.3 GB file, about 41.5 GB in use).

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

IQ3_M (31.9 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

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 byRichardErkhov
FamilyLlama
Downloads (HF)48
Last updated2024-04-28

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

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

About 35.1 GB at IQ3_M with an 8K context window. That is the 31.9 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-3-70B-Instruct 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-Instruct GGUF?

It depends on the quant: Q2_K is 26.4 GB, IQ3_XS is 29.3 GB, IQ3_S is 30.9 GB, Q3_K_S is 30.9 GB, IQ3_M is 31.9 GB, Q3_K is 34.3 GB and 3 more.

What context length does 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-3-70B-Instruct GGUF?

The files are on Hugging Face in the RichardErkhov/NousResearch_-_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.

Similar models

Browse all →

More from RichardErkhov

All by RichardErkhov →

More Llama models

All Llama →

Other large models

All large models →