VI

VideoChat3-4B

VideochatGGUF by SkyContactUpdated 2026-10-15
Download on Hugging Face
Parameters4.48B
Context256K
Layers36
Architecturevideochat3
Smallest quant4.2 GB
Quick answer

VideoChat3-4B needs about 5.9 GB of memory at Q6_K (a 4.2 GB file) with an 8K context window, so it fits on a 6 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.

VideoChat3-4B is a 4.48B-parameter Videochat model in GGUF format, quantized by SkyContact. Its trained context length is 256K tokens. The repository has 1 quant file, from 4.2 GB (Q6_K) to 4.2 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q6_K4.2 GB 5.9 GB
Fits Get file →

What GPU do you need for VideoChat3-4B?

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: the best quant that fits is Q6_K (4.2 GB file, about 5.9 GB in use).

Which VideoChat3-4B quant should you choose?

Q6_K (4.2 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

Architecturevideochat3
Parameters4.48B
Layers36
Trained context262,144 tokens
KV cache (fp16)144 KB per token

Source

Quantized bySkyContact
FamilyVideochat
Licenseapache-2.0
Downloads (HF)408
Last updated2026-10-15

Frequently asked questions about VideoChat3-4B

How much VRAM does VideoChat3-4B need?

About 5.9 GB at Q6_K with an 8K context window. That is the 4.2 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 VideoChat3-4B on an 8 GB GPU?

Yes, with Q6_K: the 4.2 GB file needs about 5.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of VideoChat3-4B GGUF?

It depends on the quant: Q6_K is 4.2 GB.

What context length does VideoChat3-4B support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.2 GB at 8K and 4.8 GB at 32K.

Where can I download VideoChat3-4B GGUF?

The files are on Hugging Face in the SkyContact/VideoChat3-4B-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 VideoChat3-4B 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 SkyContact

All by SkyContact →

More Videochat models

All Videochat →

Other small models

All small models →