LL

Llama 3.3 70B Instruct

LlamaGGUF by bgarcia3Updated 2024-12-11
Download on Hugging Face
Parameters70.6B
Context128K
Layers—
Architecturellama
Smallest quant43.3 GB
Quick answer

Llama 3.3 70B Instruct needs about 49.0 GB of memory at Q4_K_L (a 43.3 GB file) with an 8K context window, which is more than a 48 GB GPU holds.

Llama 3.3 70B Instruct is a 70.6B-parameter Llama model in GGUF format, quantized by bgarcia3. Its trained context length is 128K tokens. The repository has 1 quant file, from 43.3 GB (Q4_K_L) to 43.3 GB (Q4_K_L).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_L43.3 GB 49.0 GB
Too big Get file →

What GPU do you need for Llama 3.3 70B Instruct?

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.

Which Llama 3.3 70B Instruct quant should you choose?

Q4_K_L (43.3 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters70.6B
Trained context131,072 tokens

Source

Quantized bybgarcia3
FamilyLlama
Downloads (HF)0
Last updated2024-12-11

Frequently asked questions about Llama 3.3 70B Instruct

How much VRAM does Llama 3.3 70B Instruct need?

About 49.0 GB at Q4_K_L with an 8K context window. That is the 43.3 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 Llama 3.3 70B Instruct on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 49.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Llama 3.3 70B Instruct GGUF?

It depends on the quant: Q4_K_L is 43.3 GB.

What context length does Llama 3.3 70B Instruct support?

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

Where can I download Llama 3.3 70B Instruct GGUF?

The files are on Hugging Face in the bgarcia3/Llama-3.3-70B-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 bgarcia3

All by bgarcia3 →

More Llama models

All Llama →

Other large models

All large models →