LL

Llama_3.x_70b_Hexagon_Purple_V3

LlamaGGUF by ReadyArtUpdated 2026-03-28
Download on Hugging Face
Parameters70.6B
Context128K
Layers80
Architecturellama
Smallest quant60.4 GB
Quick answer

Llama_3.x_70b_Hexagon_Purple_V3 needs about 63.6 GB of memory at Q6_K (a 60.4 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.x_70b_Hexagon_Purple_V3 is a 70.6B-parameter Llama model in GGUF format, quantized by ReadyArt. Its trained context length is 128K tokens. The repository has 1 quant file, from 60.4 GB (Q6_K) to 60.4 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q6_K60.4 GB 63.6 GB
Too big Get file →

What GPU do you need for Llama_3.x_70b_Hexagon_Purple_V3?

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.x_70b_Hexagon_Purple_V3 quant should you choose?

Q6_K (60.4 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

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

Source

Quantized byReadyArt
FamilyLlama
Licensellama3.3
Downloads (HF)12
Last updated2026-03-28

Frequently asked questions about Llama_3.x_70b_Hexagon_Purple_V3

How much VRAM does Llama_3.x_70b_Hexagon_Purple_V3 need?

About 63.6 GB at Q6_K with an 8K context window. That is the 60.4 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.x_70b_Hexagon_Purple_V3 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 63.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Llama_3.x_70b_Hexagon_Purple_V3 GGUF?

It depends on the quant: Q6_K is 60.4 GB.

What context length does Llama_3.x_70b_Hexagon_Purple_V3 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.x_70b_Hexagon_Purple_V3 GGUF?

The files are on Hugging Face in the ReadyArt/Nexesenex_Llama_3.x_70b_Hexagon_Purple_V3-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.x_70b_Hexagon_Purple_V3 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.x_70b_Hexagon_Purple_V3

Similar models

Browse all →

More from ReadyArt

All by ReadyArt →

More Llama models

All Llama →

Other large models

All large models →