LL

Llama 3.3 70B Instruct

LlamaGGUF by hope-huiUpdated 2025-03-20
Download on Hugging Face
Parameters70B
Context128K
Layers80
Architecturellama
Smallest quant75.0 GB
Quick answer

Llama 3.3 70B Instruct needs about 78.2 GB of memory at Q8_0 (a 75.0 GB file) with an 8K context window, which is more than a 48 GB GPU holds. Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.

Llama 3.3 70B Instruct is a 70B-parameter Llama model in GGUF format, quantized by hope-hui. Its trained context length is 128K tokens. The repository has 1 quant file, from 75.0 GB (Q8_0) to 75.0 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_075.0 GB (4 parts) 78.2 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 (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: 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?

Q8_0 (75.0 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters70B
Layers80
Trained context131,072 tokens
KV cache (fp16)320 KB per token

Source

Quantized byhope-hui
FamilyLlama
Licensellama3.3
Downloads (HF)93
Last updated2025-03-20

Frequently asked questions about Llama 3.3 70B Instruct

How much VRAM does Llama 3.3 70B Instruct need?

About 78.2 GB at Q8_0 with an 8K context window. That is the 75.0 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 78.2 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: Q8_0 is 75.0 GB.

What context length does Llama 3.3 70B Instruct 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 Llama 3.3 70B Instruct GGUF?

The files are on Hugging Face in the hope-hui/Llama-3.3-70B-Instruct-Q8_0-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 Llama 3.3 70B Instruct 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.

Other GGUFs of Llama-3.3-70B-Instruct

Similar models

Browse all →

More from hope-hui

All by hope-hui →

More Llama models

All Llama →

Other large models

All large models →