ST

stay4s 14b lora

StayGGUF by miesdevriesUpdated 2026-09-30
Download on Hugging Face
Parameters14.8B
Context32K
Layers48
Architectureqwen2
Smallest quant9.0 GB
Quick answer

stay4s 14b lora needs about 11.1 GB of memory at its main file (a 9.0 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 4 quants, from 9.0 GB to 15.7 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.

Stay4S 14B Lora – a 14.8B Qwen2 model with tool usage

Stay4S 14B Lora is a 14.8B parameter Qwen2 model. It supports tool usage and was trained on a 32768 token context. The model is distributed in GGUF format.

Good at

  • Tool integration
  • Large context handling
  • Qwen2 architecture

Limits

  • No license specified
  • No vision support
  • Large memory requirement

Best for

  • Tool‑driven applications
  • Long‑form content generation
  • Context‑heavy dialogue

Who it’s for. Developers building applications that need tool integration and long context. Suitable for users with sufficient GPU memory to load the model.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—9.0 GB 11.1 GB
Too big Get file →
—9.0 GB 11.1 GB
Too big Get file →
—15.7 GB 17.8 GB
Too big Get file →
—15.7 GB 17.8 GB
Too big Get file →

For 8.99 GB files, estimated VRAM at 8 k context is 11.1 GB. For 15.7 GB files, estimate is 17.8 GB. Choose the 8.99 GB version if your GPU has around 12 GB VRAM; otherwise use the 15.7 GB version with 18 GB VRAM.

What GPU do you need for stay4s 14b lora?

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 the main file (9.0 GB file, about 11.1 GB in use).
  • 16 GB VRAM: the best quant that fits is the main file (9.0 GB file, about 11.1 GB in use).
  • 24 GB VRAM: the best quant that fits is the main file (15.7 GB file, about 17.8 GB in use).

Which stay4s 14b lora quant should you choose?

If memory is tight, the smallest file is the first one in the table at 9.0 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

Architectureqwen2
Parameters14.8B
Layers48
Trained context32,768 tokens
KV cache (fp16)192 KB per token

Source

Quantized bymiesdevries
FamilyStay
Downloads (HF)653
Last updated2026-09-30

Frequently asked questions about stay4s 14b lora

How much VRAM does stay4s 14b lora need?

About 11.1 GB at its main file with an 8K context window. That is the 9.0 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 stay4s 14b lora on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 11.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of stay4s 14b lora GGUF?

It depends on the quant: file is 9.0 GB, file is 9.0 GB, file is 15.7 GB, file is 15.7 GB.

What context length does stay4s 14b lora support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.6 GB at 8K and 6.4 GB at 32K.

Where can I download stay4s 14b lora GGUF?

The files are on Hugging Face in the miesdevries/stay4s-14b-lora repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run this model on 8 GB VRAM?

No, the smallest GGUF file requires about 11.1 GB VRAM at 8 k context, which exceeds 8 GB.

Does the model support vision?

No, the model has no vision capability.

What context length does it support?

It was trained on 32768 token context and can handle that length.

Similar models

Browse all →

More from miesdevries

All by miesdevries →

More Stay models

All Stay →

Other medium models

All medium models →