AI Model Catalogue

Google's most intelligent model, with improved reasoning and a new medium thinking level

Highest-quality text-to-speech with <200ms latency, emotion control, and 15-language support

Feed-forward neural network that directly infers all key 3D attributes of a scene.

A 17 billion parameter model with 128 experts

DA3Metric-Large metric depth estimation (Apache 2.0). Returns 16-bit PNG depth map with metric metadata.

Granite-4.0-H-Small is a 32B parameter long-context instruct model finetuned from Granite-4.0-H-Small-Base using a combination of open source instruction datasets with permissive license and internally collected synthetic datasets.

This is an optimised version of the hidream-l1 model using the pruna ai optimisation toolkit!

A 4B-parameter safety and content moderation model that classifies user prompts and assistant responses as Safe, Unsafe, or Controversial with fine-grained category labels and refusal detection. Supports 119 languages.

A unified Text-to-Speech demo featuring three powerful modes: Voice, Clone and Design

Ultralytics YOLOE-L Real-Time Seeing Anything model with 26.2M parameters. Achieves 52.6 mAP50-95 on COCO dataset. Optimized for real-time inference with 6.2 ms speed on T4 GPU..

The smartest diffusion language model up to ~800+ tps

The fastest diffusion language model with up to ~1000+ tps

Open-source Phi-3-mini-4k-instruct model from microsoft — available for download and self-hosting on Hugging Face.

Ultra-fast, cost-efficient text-to-speech with ~120ms latency and 15-language support

Object Recognition model

Universal Feed-Forward Metric 3D Reconstruction

Inspired by 90s streetwear, graffiti culture, and macabre aesthetics

Arise V2

Take a flat graphic, remove text, and get structured text layers back for editing and recomposing

Google's fast, expressive text-to-speech model with 30 voices and 70+ language support

This is a version of the MoE Qwen 3.5 35B optimised by Pruna AI.

This is a version of Qwen 3.5 27B optimised by Pruna AI.

ML model that detects acne, dark circles, wrinkles and oily skin in one go.

This is Platmoji 2, trained more to mimic emojis in an extremely similar way. (Realism in emojis go to Platmoji 1)

Ultralytics YOLOv8s worldv2 Real-Time Open-Vocabulary Object Detection model with 12.7M parameters. Achieves 37.7 mAP50-95 on COCO dataset. Optimized for real-time inference