LL

RYS Llama 3.1 8B Instruct

LlamaGGUF by smcleodUpdated 2024-08-09
Download on Hugging Face
Parameters8.68B
Context128K
Layers35
Architecturellama
Smallest quant7.1 GB
Quick answer

RYS Llama 3.1 8B Instruct needs about 8.8 GB of memory at Q6_K (a 7.1 GB file) with an 8K context window, so it fits on a 12 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 4.7 GB.

RYS Llama 3.1 8B Instruct is a 8.68B-parameter Llama model in GGUF format, quantized by smcleod. Its trained context length is 128K tokens. The repository has 1 quant file, from 7.1 GB (Q6_K) to 7.1 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q6_K7.1 GB 8.8 GB
Too big Get file →

What GPU do you need for RYS Llama 3.1 8B 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: the best quant that fits is Q6_K (7.1 GB file, about 8.8 GB in use).

Which RYS Llama 3.1 8B Instruct quant should you choose?

Q6_K (7.1 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
Parameters8.68B
Layers35
Trained context131,072 tokens
KV cache (fp16)140 KB per token

Source

Quantized bysmcleod
FamilyLlama
Licensemit
Downloads (HF)27
Last updated2024-08-09

Frequently asked questions about RYS Llama 3.1 8B Instruct

How much VRAM does RYS Llama 3.1 8B Instruct need?

About 8.8 GB at Q6_K with an 8K context window. That is the 7.1 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 RYS Llama 3.1 8B Instruct on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 8.8 GB, so you would need a larger GPU or CPU offloading.

What is the file size of RYS Llama 3.1 8B Instruct GGUF?

It depends on the quant: Q6_K is 7.1 GB.

What context length does RYS Llama 3.1 8B 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 1.2 GB at 8K and 4.7 GB at 32K.

Where can I download RYS Llama 3.1 8B Instruct GGUF?

The files are on Hugging Face in the smcleod/RYS-Llama-3.1-8B-Instruct-Q6_K-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 RYS Llama 3.1 8B Instruct 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.

Other GGUFs of RYS-Llama-3.1-8B-Instruct

Similar models

Browse all →

More from smcleod

All by smcleod →

More Llama models

All Llama →

Other small models

All small models →