ZE

DarkArtsForge Zepar 24B v1 IQ3 KT attn

ZeparGGUF by KoshkasaUpdated 2026-07-25
Download on Hugging Face
Parameters23.6B
Context128K
Layers40
Architecturellama
Smallest quant11.0 GB
Quick answer

DarkArtsForge Zepar 24B v1 IQ3 KT attn needs about 12.8 GB of memory at its main file (a 11.0 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 2 quants, from 11.0 GB to 47.2 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

DarkArtsForge Zepar 24B v1 IQ3 KT attn is a 23.6B-parameter Zepar model in GGUF format, quantized by Koshkasa. Its trained context length is 128K tokens. The repository has 2 quant files, from 11.0 GB to 47.2 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—11.0 GB 12.8 GB
Too big Get file →
F1647.2 GB 49.0 GB
Too big Get file →

What GPU do you need for DarkArtsForge Zepar 24B v1 IQ3 KT attn?

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: no quant fits at an 8K context.
  • 16 GB VRAM: the best quant that fits is the main file (11.0 GB file, about 12.8 GB in use).
  • 24 GB VRAM: the best quant that fits is the main file (11.0 GB file, about 12.8 GB in use).
  • 32 GB VRAM: the best quant that fits is the main file (11.0 GB file, about 12.8 GB in use).
  • 48 GB VRAM: the best quant that fits is the main file (11.0 GB file, about 12.8 GB in use).

Specifications

Architecture from the GGUF header

Architecturellama
Parameters23.6B
Layers40
Trained context131,072 tokens
KV cache (fp16)160 KB per token

Source

Quantized byKoshkasa
FamilyZepar
Licenseapache-2.0
Downloads (HF)75
Last updated2026-07-25

Frequently asked questions about DarkArtsForge Zepar 24B v1 IQ3 KT attn

How much VRAM does DarkArtsForge Zepar 24B v1 IQ3 KT attn need?

About 12.8 GB at its main file with an 8K context window. That is the 11.0 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 DarkArtsForge Zepar 24B v1 IQ3 KT attn on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 12.8 GB, so you would need a larger GPU or CPU offloading.

What is the file size of DarkArtsForge Zepar 24B v1 IQ3 KT attn GGUF?

It depends on the quant: file is 11.0 GB, F16 is 47.2 GB.

What context length does DarkArtsForge Zepar 24B v1 IQ3 KT attn support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.3 GB at 8K and 5.4 GB at 32K.

Where can I download DarkArtsForge Zepar 24B v1 IQ3 KT attn GGUF?

The files are on Hugging Face in the Koshkasa/DarkArtsForge_Zepar-24B-v1_IQ3_KT_attn repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does DarkArtsForge Zepar 24B v1 IQ3 KT attn 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.

Other GGUFs of Zepar-24B-v1

Similar models

Browse all →

More from Koshkasa

All by Koshkasa →

More Zepar models

All Zepar →

Other medium models

All medium models →