DA

DaVinci MagiHuman fp8 merges

DavinciGGUF by realrebelaiUpdated 2026-04-02
Download on Hugging Face
Parameters9.24B
Context—
Layers—
Architecturegemma
Smallest quant11.9 GB
Quick answer

DaVinci MagiHuman fp8 merges needs about 13.9 GB of memory at Q6_K (a 11.9 GB file) with an 8K context window, so it fits on a 16 GB GPU.

DaVinci MagiHuman fp8 merges is a 9.24B-parameter Davinci model in GGUF format, quantized by realrebelai. The repository has 1 quant file, from 11.9 GB (Q6_K) to 11.9 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q6_K11.9 GB 13.9 GB
Too big Get file →

What GPU do you need for DaVinci MagiHuman fp8 merges?

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: 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 Q6_K (11.9 GB file, about 13.9 GB in use).

Which DaVinci MagiHuman fp8 merges quant should you choose?

Q6_K (11.9 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.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegemma
Parameters9.24B

Source

Quantized byrealrebelai
FamilyDavinci
Licenseapache-2.0
Downloads (HF)37
Last updated2026-04-02

Frequently asked questions about DaVinci MagiHuman fp8 merges

How much VRAM does DaVinci MagiHuman fp8 merges need?

About 13.9 GB at Q6_K with an 8K context window. That is the 11.9 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 DaVinci MagiHuman fp8 merges on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 13.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of DaVinci MagiHuman fp8 merges GGUF?

It depends on the quant: Q6_K is 11.9 GB.

Where can I download DaVinci MagiHuman fp8 merges GGUF?

The files are on Hugging Face in the realrebelai/DaVinci_MagiHuman_fp8_merges repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does DaVinci MagiHuman fp8 merges 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 →

More from realrebelai

All by realrebelai →

More Davinci models

All Davinci →

Other small models

All small models →