CO

Cogidonia v2 24B imatrix

CogidoniaGGUF by MRockatanskyUpdated 2026-07-25
Download on Hugging Face
Parameters23.6B
Context128K
Layers40
Architecturellama
Smallest quant10.6 GB
Quick answer

Cogidonia v2 24B imatrix needs about 17.3 GB of memory at Q4_K_M (a 15.5 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 4 quants, from 10.6 GB (IQ3_XXS) to 19.3 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

Cogidonia v2 24B imatrix is a 23.6B-parameter Cogidonia model in GGUF format, quantized by MRockatansky. Its trained context length is 128K tokens. The repository has 4 quant files, from 10.6 GB (IQ3_XXS) to 19.3 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ3_XXS10.6 GB 12.4 GB
Too big Get file →
IQ4_XS13.9 GB 15.7 GB
Too big Get file →
Q4_K_M15.5 GB 17.3 GB
Too big Get file →
Q6_K19.3 GB 21.2 GB
Too big Get file →

What GPU do you need for Cogidonia v2 24B imatrix?

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 IQ4_XS (13.9 GB file, about 15.7 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K (19.3 GB file, about 21.2 GB in use).

Which Cogidonia v2 24B imatrix quant should you choose?

Q4_K_M is the usual starting point for Cogidonia v2 24B imatrix: it balances file size and quality well. Here it is a 15.5 GB file.

If memory is tight, the smallest file is IQ3_XXS at 10.6 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

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

Source

Quantized byMRockatansky
FamilyCogidonia
Licenseapache-2.0
Downloads (HF)49
Last updated2026-07-25

Frequently asked questions about Cogidonia v2 24B imatrix

How much VRAM does Cogidonia v2 24B imatrix need?

About 17.3 GB at Q4_K_M with an 8K context window. That is the 15.5 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 Cogidonia v2 24B imatrix on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 12.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Cogidonia v2 24B imatrix GGUF?

It depends on the quant: IQ3_XXS is 10.6 GB, IQ4_XS is 13.9 GB, Q4_K_M is 15.5 GB, Q6_K is 19.3 GB.

What context length does Cogidonia v2 24B imatrix 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 Cogidonia v2 24B imatrix GGUF?

The files are on Hugging Face in the MRockatansky/Cogidonia-v2-24B-imatrix-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Cogidonia v2 24B imatrix 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 Cogidonia-v2-24B

Similar models

Browse all →

More from MRockatansky

All by MRockatansky →

More Cogidonia models

All Cogidonia →

Other medium models

All medium models →