CO

Cosmos Predict2 14B Text2Image

CosmosGGUF by city96Updated 2025-06-14
Download on Hugging Face
Parameters14.3B
Context—
Layers—
Architecturecosmos
Smallest quant6.3 GB
Quick answer

Cosmos Predict2 14B Text2Image needs about 11.1 GB of memory at Q4_K_M (a 9.5 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 13 quants, from 6.3 GB (Q3_K_S) to 28.5 GB (BF16).

Cosmos Predict2 14B Text2Image is a 14.3B-parameter Cosmos model in GGUF format, quantized by city96. The repository has 13 quant files, from 6.3 GB (Q3_K_S) to 28.5 GB (BF16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_S6.3 GB 7.6 GB
Tight Get file →
Q3_K_M7.0 GB 8.3 GB
Too big Get file →
Q4_08.4 GB 9.9 GB
Too big Get file →
Q4_K_S8.7 GB 10.2 GB
Too big Get file →
Q4_19.1 GB 10.7 GB
Too big Get file →
Q4_K_M9.5 GB 11.1 GB
Too big Get file →
Q5_K_S10.0 GB 11.6 GB
Too big Get file →
Q5_010.2 GB 11.9 GB
Too big Get file →
Q5_K_M10.6 GB 12.4 GB
Too big Get file →
Q5_110.8 GB 12.6 GB
Too big Get file →
Q6_K11.8 GB 13.8 GB
Too big Get file →
Q8_015.3 GB 17.6 GB
Too big Get file →
BF1628.5 GB 32.5 GB
Too big Get file →

What GPU do you need for Cosmos Predict2 14B Text2Image?

These figures add the file size, an fp16 KV cache at an 8K context window 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: the best quant that fits is Q3_K_S (6.3 GB file, about 7.6 GB in use).
  • 12 GB VRAM: the best quant that fits is Q5_0 (10.2 GB file, about 11.9 GB in use).
  • 16 GB VRAM: the best quant that fits is Q6_K (11.8 GB file, about 13.8 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (15.3 GB file, about 17.6 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (15.3 GB file, about 17.6 GB in use).
  • 48 GB VRAM: the best quant that fits is BF16 (28.5 GB file, about 32.5 GB in use).

Which Cosmos Predict2 14B Text2Image quant should you choose?

Q4_K_M is the usual starting point for Cosmos Predict2 14B Text2Image: it balances file size and quality well. Here it is a 9.5 GB file.

The Q8_0 file is 15.3 GB, about 1.6 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q3_K_S at 6.3 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

Architecturecosmos
Parameters14.3B

Source

Quantized bycity96
FamilyCosmos
Licenseother
Downloads (HF)3,160
Last updated2025-06-14

Frequently asked questions about Cosmos Predict2 14B Text2Image

How much VRAM does Cosmos Predict2 14B Text2Image need?

About 11.1 GB at Q4_K_M with an 8K context window. That is the 9.5 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 Cosmos Predict2 14B Text2Image on an 8 GB GPU?

Yes, with Q3_K_S: the 6.3 GB file needs about 7.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Cosmos Predict2 14B Text2Image GGUF?

It depends on the quant: Q3_K_S is 6.3 GB, Q3_K_M is 7.0 GB, Q4_0 is 8.4 GB, Q4_K_S is 8.7 GB, Q4_1 is 9.1 GB, Q4_K_M is 9.5 GB and 7 more.

Where can I download Cosmos Predict2 14B Text2Image GGUF?

The files are on Hugging Face in the city96/Cosmos-Predict2-14B-Text2Image-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 Cosmos Predict2 14B Text2Image use?

Hugging Face lists the license as other. 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 →

More from city96

All by city96 →

More Cosmos models

All Cosmos →

Other medium models

All medium models →