LL

Llama 3 IMPACTS 2x8B 64k

LlamaGGUF by SeverianUpdated 2024-05-04
Download on Hugging Face
Parameters13.7B
Context64K
Layers32
Architecturellama
Smallest quant27.3 GB
Quick answer

Llama 3 IMPACTS 2x8B 64k needs about 28.9 GB of memory at F16 (a 27.3 GB file) with an 8K context window, so it fits on a 32 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Llama 3 IMPACTS 2x8B 64k is a 13.7B-parameter Llama model in GGUF format, quantized by Severian. Its trained context length is 64K tokens. The repository has 1 quant file, from 27.3 GB (F16) to 27.3 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F1627.3 GB 28.9 GB
Too big Get file →

What GPU do you need for Llama 3 IMPACTS 2x8B 64k?

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: the best quant that fits is F16 (27.3 GB file, about 28.9 GB in use).

Which Llama 3 IMPACTS 2x8B 64k quant should you choose?

F16 (27.3 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters13.7B (approximate, mixture of experts)
Layers32
Trained context65,536 tokens
KV cache (fp16)128 KB per token

Source

Quantized bySeverian
FamilyLlama
Licensemit
Downloads (HF)45
Last updated2024-05-04

Frequently asked questions about Llama 3 IMPACTS 2x8B 64k

How much VRAM does Llama 3 IMPACTS 2x8B 64k need?

About 28.9 GB at F16 with an 8K context window. That is the 27.3 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 IMPACTS 2x8B 64k on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 28.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Llama 3 IMPACTS 2x8B 64k GGUF?

It depends on the quant: F16 is 27.3 GB.

What context length does Llama 3 IMPACTS 2x8B 64k support?

The GGUF header lists a trained context length of 65,536 tokens (64K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download Llama 3 IMPACTS 2x8B 64k GGUF?

The files are on Hugging Face in the Severian/Llama-3-IMPACTS-2x8B-64k-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 IMPACTS 2x8B 64k use?

Hugging Face lists the license as mit. 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 Severian

All by Severian →

More Llama models

All Llama →

Other medium models

All medium models →