YOLO-Face-Person-Detector
Will it run on your hardware?
Pick your GPU memory - see which quantizations fit, and the cheapest card for the rest
Need an exact figure for your context length? Use the VRAM calculator.
Run it locally
Copy-paste - running in under a minute
vllm serve iitolstykh/YOLO-Face-Person-DetectorNew to this? Start with Ollama · serve to many users with vLLM.
Deep dive
Notes, sources, and the full write-up
YOLO-Face-Person-Detector is an open-weight object detection model from iitolstykh, published on Hugging Face in November 2025. It has 70M parameters and is released under the agpl-3.0 license.
HardwareLink to this section
At full FP16 precision the weights need about 1 GB of memory; 8-bit quantization brings that to roughly 1 GB. That is small enough for most consumer GPUs, Apple Silicon Macs, and many CPUs.
PopularityLink to this section
YOLO-Face-Person-Detector had 66,474 downloads on Hugging Face in the last month and has 27 likes.
Run it locallyLink to this section
The weights are on Hugging Face and load with ultralytics. Follow the model card for the exact setup and license terms.
Frequently asked
Quick answers to common questions
How much VRAM does YOLO-Face-Person-Detector need?
YOLO-Face-Person-Detector with 0.07B parameters needs approximately 1 GB at Q4_K_M quantization. Use our VRAM calculator for an exact estimate.
Is YOLO-Face-Person-Detector better than other iitolstykh models?
YOLO-Face-Person-Detector has 0.07B parameters with 8,192 context - a strong choice for object-detection.
What license is YOLO-Face-Person-Detector under?
YOLO-Face-Person-Detector is released under the agpl-3.0 license, making it suitable for most commercial and personal projects.
What hardware runs YOLO-Face-Person-Detector well?
With 0.07B parameters, YOLO-Face-Person-Detector 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 YOLO-Face-Person-Detector?
Q4_K_M is the recommended sweet spot - ~98% of FP16 quality at ~27% of the size. Q5_K_M (~1 GB) is an option if you have spare VRAM. Use our VRAM calculator to compare.
What models compete with YOLO-Face-Person-Detector?
YOLO-Face-Person-Detector 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