LL

llama33 70B

LlamaGGUF by TwobombsUpdated 2024-12-07
Download on Hugging Face
Parameters70.6B
Context128K
Layers—
Architecturellama
Smallest quant42.5 GB
Quick answer

llama33 70B needs about 48.1 GB of memory at its main file (a 42.5 GB file) with an 8K context window, which is more than a 48 GB GPU holds.

llama33 70B is a 70.6B-parameter Llama model in GGUF format, quantized by Twobombs. Its trained context length is 128K tokens. The repository has 1 quant file, from 42.5 GB to 42.5 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—42.5 GB 48.1 GB
Too big Get file →

What GPU do you need for llama33 70B?

These figures add the file size, an fp16 KV cache at an 8K context window 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.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters70.6B
Trained context131,072 tokens

Source

Quantized byTwobombs
FamilyLlama
Licensellama3.3
Downloads (HF)19
Last updated2024-12-07

Frequently asked questions about llama33 70B

How much VRAM does llama33 70B need?

About 48.1 GB at its main file 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 llama33 70B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 48.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of llama33 70B GGUF?

It depends on the quant: file is 42.5 GB.

What context length does llama33 70B support?

The GGUF header lists a trained context length of 131,072 tokens (128K).

Where can I download llama33 70B GGUF?

The files are on Hugging Face in the Twobombs/llama33-70B repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does llama33 70B use?

Hugging Face lists the license as llama3.3. 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 Twobombs

All by Twobombs →

More Llama models

All Llama →

Other large models

All large models →