DK

DKVSL lemonade server

DkvslGGUF by danidarkoUpdated 2026-07-21
Download on Hugging Face
Parameters12.8B
Context40K
Layers36
Architectureqwen3
Smallest quant2.5 GB
Quick answer

DKVSL lemonade server needs about 4.2 GB of memory at Q4_K_M (a 2.5 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 3 quants, from 2.5 GB (Q4_K_M) to 9.9 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.

DKVSL lemonade server is a 12.8B-parameter Dkvsl model in GGUF format, quantized by danidarko. Its trained context length is 40K tokens. The repository has 3 quant files, from 2.5 GB (Q4_K_M) to 9.9 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M2.5 GB 4.2 GB
Fits Get file →
—7.2 GB 8.9 GB
Too big Get file →
—9.9 GB 11.6 GB
Too big Get file →

What GPU do you need for DKVSL lemonade server?

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: the best quant that fits is Q4_K_M (2.5 GB file, about 4.2 GB in use).
  • 8 GB VRAM: the best quant that fits is Q4_K_M (2.5 GB file, about 4.2 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (9.9 GB file, about 11.6 GB in use).

Which DKVSL lemonade server quant should you choose?

Q4_K_M is the usual starting point for DKVSL lemonade server: it balances file size and quality well. Here it is a 2.5 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen3
Parameters12.8B
Layers36
Trained context40,960 tokens
KV cache (fp16)144 KB per token

Source

Quantized bydanidarko
FamilyDkvsl
Licenseapache-2.0
Downloads (HF)25
Last updated2026-07-21

Frequently asked questions about DKVSL lemonade server

How much VRAM does DKVSL lemonade server need?

About 4.2 GB at Q4_K_M with an 8K context window. That is the 2.5 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 DKVSL lemonade server on an 8 GB GPU?

Yes, with Q4_K_M: the 2.5 GB file needs about 4.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of DKVSL lemonade server GGUF?

It depends on the quant: Q4_K_M is 2.5 GB, file is 7.2 GB, file is 9.9 GB.

What context length does DKVSL lemonade server support?

The GGUF header lists a trained context length of 40,960 tokens (40K). The KV cache grows with the context you use: about 1.2 GB at 8K and 4.8 GB at 32K.

Where can I download DKVSL lemonade server GGUF?

The files are on Hugging Face in the danidarko/DKVSL-lemonade-server repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does DKVSL lemonade server 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.

Similar models

Browse all →

Other medium models

All medium models →