SS

ssiat 1.0

SsiatGGUF by MOGODIKUpdated 2026-09-20
Download on Hugging Face
Parameters255M
Context1K
Layers16
Architecturellama
Smallest quant0.5 GB
Quick answer

ssiat 1.0 needs about 1.5 GB of memory at its main file (a 0.5 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 3 quants, from 0.5 GB to 0.5 GB.

254.7M Korean‑only Llama model for character chatbots

Ssiat 1.0 is a 0.255B parameter Llama model focused on Korean language. It is lightweight, with a 1024 token context window and an Apache‑2.0 license. The model is designed for easy fine‑tuning and local deployment.

Good at

  • Character consistency
  • Fast fine‑tuning
  • Low resource usage

Limits

  • No vision support
  • Ollama may produce incorrect outputs
  • Context limited to 1024 tokens

Best for

  • Building Korean character chatbots
  • Educational LLM experiments
  • Rapid prototyping on consumer GPUs

Who it’s for. Developers and students who need a small, Korean‑only LLM that can be trained and run on modest hardware. The model is suitable for those who want to experiment with character personalities without large API costs.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.5 GB 1.1 GB
Fits Get file →
—0.5 GB 1.1 GB
Fits Get file →
—0.5 GB 1.1 GB
Fits Get file →

Each GGUF file is 0.51 GB and requires about 1.5 GB of VRAM at 8 k context. For 8 GB VRAM, run the full model. For 4 GB VRAM, consider a lower‑precision quant if available. The provided files are unquantized, so memory usage is as estimated.

What GPU do you need for ssiat 1.0?

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: the best quant that fits is the main file (0.5 GB file, about 1.5 GB in use).

Which ssiat 1.0 quant should you choose?

If memory is tight, the smallest file is the first one in the table at 0.5 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters255M
Layers16
Trained context1,024 tokens
KV cache (fp16)64 KB per token

Source

Quantized byMOGODIK
FamilySsiat
Licenseapache-2.0
Downloads (HF)631
Last updated2026-09-20

Frequently asked questions about ssiat 1.0

How much VRAM does ssiat 1.0 need?

About 1.5 GB at its main file with an 8K context window. That is the 0.5 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 ssiat 1.0 on an 8 GB GPU?

Yes, with the smaller files: the 0.5 GB file needs about 1.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of ssiat 1.0 GGUF?

It depends on the quant: file is 0.5 GB, file is 0.5 GB, file is 0.5 GB.

What context length does ssiat 1.0 support?

The GGUF header lists a trained context length of 1,024 tokens (1K). The KV cache grows with the context you use: about 0.5 GB at 8K and 0.1 GB at 1K.

Where can I download ssiat 1.0 GGUF?

The files are on Hugging Face in the MOGODIK/ssiat-1.0 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does ssiat 1.0 use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run Ssiat 1.0 on 8 GB VRAM?

Yes, the model requires about 1.5 GB of VRAM at 8 k context, so 8 GB is more than sufficient.

Will Ollama work with this model?

Ollama may produce incorrect or broken outputs due to pre‑tokenizer issues. Use llama.cpp directly.

What is the context length of Ssiat 1.0?

The trained context length is 1024 tokens.

Similar models

Browse all →

Other tiny models

All tiny models →