CH

Chroma

ChromaGGUF by ClybiusUpdated 2025-04-29
Download on Hugging Face
Parameters8.9B
Context—
Layers—
Architectureflux
Smallest quant5.4 GB
Quick answer

Chroma needs about 9.1 GB of memory at Q6_K (a 7.7 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 6 quants, from 5.4 GB (Q4_K_S) to 9.3 GB.

Chroma is a 8.9B-parameter Chroma model in GGUF format, quantized by Clybius. The repository has 6 quant files, from 5.4 GB (Q4_K_S) to 9.3 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_S5.4 GB 6.6 GB
Fits Get file →
Q4_K_S5.4 GB 6.6 GB
Fits Get file →
Q6_K7.7 GB 9.1 GB
Too big Get file →
Q6_K7.7 GB 9.1 GB
Too big Get file →
—9.3 GB 10.9 GB
Too big Get file →
—9.3 GB 10.9 GB
Too big Get file →

What GPU do you need for Chroma?

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 Q4_K_S (5.4 GB file, about 6.6 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (9.3 GB file, about 10.9 GB in use).

Which Chroma quant should you choose?

Q6_K (7.7 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.

If memory is tight, the smallest file is Q4_K_S at 5.4 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureflux
Parameters8.9B

Source

Quantized byClybius
FamilyChroma
Licenseapache-2.0
Downloads (HF)367
Last updated2025-04-29

Frequently asked questions about Chroma

How much VRAM does Chroma need?

About 9.1 GB at Q6_K with an 8K context window. That is the 7.7 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 Chroma on an 8 GB GPU?

Yes, with Q4_K_S: the 5.4 GB file needs about 6.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Chroma GGUF?

It depends on the quant: Q4_K_S is 5.4 GB, Q4_K_S is 5.4 GB, Q6_K is 7.7 GB, Q6_K is 7.7 GB, file is 9.3 GB, file is 9.3 GB.

Where can I download Chroma GGUF?

The files are on Hugging Face in the Clybius/Chroma-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 Chroma 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 Chroma

Similar models

Browse all →

More from Clybius

All by Clybius →

More Chroma models

All Chroma →

Other small models

All small models →