krea-realtime-video
kreaapache-2.0textvideo

krea-realtime-video

Updated Nov 21, 2026
Parameters
14.3B
License
apache-2.0
Updated
Nov 21, 2026

Will it run on your hardware?

Pick your GPU memory - see which quantizations fit, and the cheapest card for the rest

Runs on your 24 GB - best at Q8_0
3 of 4 quantizations fit krea-realtime-video with real runtime overhead.
Q4_K_M
8 GB
Q5_K_M
10 GB
Q8_0
15 GB
fits tight too big

Need an exact figure for your context length? Use the VRAM calculator.

Run it locally

Copy-paste - running in under a minute

vLLMOpenAI-compatible API
vllm serve krea/krea-realtime-video

New to this? Start with Ollama · serve to many users with vLLM.

Deep dive

Notes, sources, and the full write-up

krea-realtime-video is an open-weight video generation model published by krea on Hugging Face in October 2025, with 14.3B parameters under the apache-2.0 license. It is built on Wan-AI/Wan2.1-T2V-14B.

Among the 24 video generation models in this directory it ranks 23rd by monthly Hugging Face downloads, and 8 of the others are larger.

HardwareLink to this section

Unquantized FP16 weights take about 29 GB; 8-bit brings that to ~15 GB and 4-bit (Q4_K_M) to ~8 GB, before activations and any context or image buffers. A 12 GB consumer card holds it at 4-bit; FP16 needs a workstation GPU or multi-GPU setup. Check exact numbers for your card with the VRAM calculator.

Similar video generation modelsLink to this section

PopularityLink to this section

krea-realtime-video was downloaded 7,334 times on Hugging Face in the last month (54,271 all-time) and has 315 likes.

Run it locallyLink to this section

Weights and usage instructions are on the krea/krea-realtime-video model card; it loads with Hugging Face Diffusers (or ComfyUI).

Local runtimes that fit this model:

  • comfyui - node-based workflows, the usual way to run diffusion models locally
  • invokeai - a canvas UI for image generation and editing

Frequently asked

Quick answers to common questions

How much VRAM does krea-realtime-video need?

krea-realtime-video with 14.3B parameters needs approximately 8 GB at Q4_K_M quantization. Use our VRAM calculator for an exact estimate.

Is krea-realtime-video better than other krea models?

krea-realtime-video has 14.3B parameters - a strong choice for video-generation.

What license is krea-realtime-video under?

krea-realtime-video is released under the apache-2.0 license, making it suitable for most commercial and personal projects.

What hardware runs krea-realtime-video well?

With 14.3B parameters, krea-realtime-video requires adequate VRAM. High-end GPUs like the RTX 4090 (24GB), RTX 5090 (32GB), or Mac Studio with unified memory are good options. Check our hardware directory for specific recommendations.

What is the best quantization for krea-realtime-video?

Q4_K_M is the recommended sweet spot - ~98% of FP16 quality at ~27% of the size. Q5_K_M (~10 GB) is an option if you have spare VRAM. Use our VRAM calculator to compare.

What models compete with krea-realtime-video?

krea-realtime-video competes with other models in its class. Browse our model directory for comparisons, benchmarks, and community reviews to find the best fit.

Nearby options

Similar models and compatible hardware by spec