CG

cgcengine models

CgcengineGGUF by AlexchuangUpdated 2026-08-31
Download on Hugging Face
Parameters25.2B
Context256K
Layers30
Architecturegemma4
Smallest quant11.3 GB
Quick answer

cgcengine models needs about 21.8 GB of memory at IQ3_XXS (a 13.2 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 6 quants, from 11.3 GB (IQ3_S) to 15.3 GB (IQ3_XXS). Longer context needs more: at 32K tokens the KV cache alone adds about 32.2 GB.

cgcengine models is a 25.2B-parameter Cgcengine model in GGUF format, quantized by Alexchuang. Its trained context length is 256K tokens. The repository has 6 quant files, from 11.3 GB (IQ3_S) to 15.3 GB (IQ3_XXS).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ3_S11.3 GB 19.8 GB
Too big Get file →
IQ3_S12.0 GB 20.5 GB
Too big Get file →
IQ3_XXS13.2 GB 21.8 GB
Too big Get file →
IQ3_XXS13.7 GB 22.2 GB
Too big Get file →
IQ3_XXS14.1 GB 22.6 GB
Too big Get file →
IQ3_XXS15.3 GB 23.9 GB
Too big Get file →

What GPU do you need for cgcengine models?

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: no quant fits at an 8K context.
  • 24 GB VRAM: the best quant that fits is IQ3_XXS (15.3 GB file, about 23.9 GB in use).

Which cgcengine models quant should you choose?

IQ3_XXS (13.2 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

If memory is tight, the smallest file is IQ3_S at 11.3 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegemma4
Parameters25.2B (approximate, mixture of experts)
Layers30
Trained context262,144 tokens
KV cache (fp16)960 KB per token

Source

Quantized byAlexchuang
FamilyCgcengine
Licenseapache-2.0
Downloads (HF)52
Last updated2026-08-31

Frequently asked questions about cgcengine models

How much VRAM does cgcengine models need?

About 21.8 GB at IQ3_XXS with an 8K context window. That is the 13.2 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 cgcengine models on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 19.8 GB, so you would need a larger GPU or CPU offloading.

What is the file size of cgcengine models GGUF?

It depends on the quant: IQ3_S is 11.3 GB, IQ3_S is 12.0 GB, IQ3_XXS is 13.2 GB, IQ3_XXS is 13.7 GB, IQ3_XXS is 14.1 GB, IQ3_XXS is 15.3 GB.

What context length does cgcengine models support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 8.1 GB at 8K and 32.2 GB at 32K.

Where can I download cgcengine models GGUF?

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

What license does cgcengine models 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 →