LL

KoSafeGuard 8b 0503

LlamaGGUF by heegyuUpdated 2024-10-25
Download on Hugging Face
Parameters8.03B
Context8K
Layers32
Architecturellama
Smallest quant4.9 GB
Quick answer

KoSafeGuard 8b 0503 needs about 6.5 GB of memory at Q4_K_M (a 4.9 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 2 quants, from 4.9 GB (Q4_K_M) to 5.7 GB (Q5_K_M).

KoSafeGuard 8b 0503 is a 8.03B-parameter Llama model in GGUF format, quantized by heegyu. Its trained context length is 8K tokens. The repository has 2 quant files, from 4.9 GB (Q4_K_M) to 5.7 GB (Q5_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M4.9 GB 6.5 GB
Fits Get file →
Q5_K_M5.7 GB 7.3 GB
Tight Get file →

What GPU do you need for KoSafeGuard 8b 0503?

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: the best quant that fits is Q5_K_M (5.7 GB file, about 7.3 GB in use).

Which KoSafeGuard 8b 0503 quant should you choose?

Q4_K_M is the usual starting point for KoSafeGuard 8b 0503: it balances file size and quality well. Here it is a 4.9 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters8.03B
Layers32
Trained context8,192 tokens
KV cache (fp16)128 KB per token

Source

Quantized byheegyu
FamilyLlama
Licensellama3
Downloads (HF)151
Last updated2024-10-25

Frequently asked questions about KoSafeGuard 8b 0503

How much VRAM does KoSafeGuard 8b 0503 need?

About 6.5 GB at Q4_K_M with an 8K context window. That is the 4.9 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 KoSafeGuard 8b 0503 on an 8 GB GPU?

Yes, with Q5_K_M: the 5.7 GB file needs about 7.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of KoSafeGuard 8b 0503 GGUF?

It depends on the quant: Q4_K_M is 4.9 GB, Q5_K_M is 5.7 GB.

What context length does KoSafeGuard 8b 0503 support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 1.1 GB at 8K and 1.1 GB at 8K.

Where can I download KoSafeGuard 8b 0503 GGUF?

The files are on Hugging Face in the heegyu/KoSafeGuard-8b-0503 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does KoSafeGuard 8b 0503 use?

Hugging Face lists the license as llama3. 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-Ko-8B-Instruct

Similar models

Browse all →

More from heegyu

All by heegyu →

More Llama models

All Llama →

Other small models

All small models →