LL

Meta Llama 3.1 70B Instruct IQ 1S

LlamaGGUF by npc0Updated 2024-08-26
Download on Hugging Face
Parameters70.6B
Context128K
Layers80
Architecturellama
Smallest quant15.3 GB
Quick answer

Meta Llama 3.1 70B Instruct IQ 1S needs about 18.5 GB of memory at its main file (a 15.3 GB file) with an 8K context window, so it fits on a 24 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.

Meta Llama 3.1 70B Instruct IQ 1S is a 70.6B-parameter Llama model in GGUF format, quantized by npc0. Its trained context length is 128K tokens. The repository has 1 quant file, from 15.3 GB to 15.3 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—15.3 GB 18.5 GB
Too big Get file →

What GPU do you need for Meta Llama 3.1 70B Instruct IQ 1S?

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 the main file (15.3 GB file, about 18.5 GB in use).

Specifications

Architecture from the GGUF header

Architecturellama
Parameters70.6B
Layers80
Trained context131,072 tokens
KV cache (fp16)320 KB per token

Source

Quantized bynpc0
FamilyLlama
Licensellama3.1
Downloads (HF)9
Last updated2024-08-26

Frequently asked questions about Meta Llama 3.1 70B Instruct IQ 1S

How much VRAM does Meta Llama 3.1 70B Instruct IQ 1S need?

About 18.5 GB at its main file with an 8K context window. That is the 15.3 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 3.1 70B Instruct IQ 1S 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 3.1 70B Instruct IQ 1S GGUF?

It depends on the quant: file is 15.3 GB.

What context length does Meta Llama 3.1 70B Instruct IQ 1S support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 2.7 GB at 8K and 10.7 GB at 32K.

Where can I download Meta Llama 3.1 70B Instruct IQ 1S GGUF?

The files are on Hugging Face in the npc0/Meta-Llama-3.1-70B-Instruct-IQ_1S 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 3.1 70B Instruct IQ 1S use?

Hugging Face lists the license as llama3.1. 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 Llama-3.1-70B-Instruct

Similar models

Browse all →

More from npc0

All by npc0 →

More Llama models

All Llama →

Other large models

All large models →