AI Model Catalogue

BiRefNet + Cutie video segmentation with stacked output video

Generate videos guided by reference images using xAI's Grok Imagine Video model

Max-quality image generation and editing with support for ten reference images

GPU accelerated replay renderer / video data clipper for comma.ai connect's openpilot route data. SEE README.

Super video quality enhancement featuring fast upscaling with TensorRT and frame interpolation with RIFE.

Extend videos with xAI's Grok Imagine Video model. Provide a source video and describe what happens next.

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

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

Fastest image upscaler in the world (<1s) supporting outputs up to 128 MP.

Open-source OTel-LLM-1B-IT model from farbodtavakkoli — available for download and self-hosting on Hugging Face.

Open-source OTel-LLM-0.6B-IT model from farbodtavakkoli — available for download and self-hosting on Hugging Face.

Open-source tiny-gpt2 model from sshleifer — available for download and self-hosting on Hugging Face.

Open-source Llama-3.2-1B-Instruct-FP8 model from redhatai — available for download and self-hosting on Hugging Face.

Open-source DeepSeek-V2-Lite-Chat model from deepseek-ai — available for download and self-hosting on Hugging Face.

Open-source Llama-3.2-1B-Instruct-Q8_0-GGUF model from hugging-quants — available for download and self-hosting on Hugging Face.

Open-source Qwen3-Coder-Next-FP8 model from qwen — available for download and self-hosting on Hugging Face.

Open-source NVIDIA-Nemotron-3-Nano-30B-A3B-FP8 model from nvidia — available for download and self-hosting on Hugging Face.

glm-5 — available to run locally via Ollama on CPU and GPU hardware.

deepseek-v3.2 — available to run locally via Ollama on CPU and GPU hardware.

qwen3-vl:235b — available to run locally via Ollama on CPU and GPU hardware.

cogito-2.1:671b — available to run locally via Ollama on CPU and GPU hardware.

Open-source Mistral-7B-Instruct-v0.2 model from mistralai — available for download and self-hosting on Hugging Face.

Open-source Qwen3-0.6B-FP8 model from qwen — available for download and self-hosting on Hugging Face.

Open-source Llama-3.1-8B model from meta-llama — available for download and self-hosting on Hugging Face.

Open-source OTel-LLM-1.2B-IT model from farbodtavakkoli — available for download and self-hosting on Hugging Face.

Open-source Gemma-4-31B-IT-NVFP4 model from nvidia — available for download and self-hosting on Hugging Face.

Open-source Qwen2.5-Coder-32B-Instruct model from qwen — available for download and self-hosting on Hugging Face.

Open-source tiny-random-Llama-3 model from llamafactory — available for download and self-hosting on Hugging Face.

Open-source Qwen3-4B-Base model from qwen — available for download and self-hosting on Hugging Face.

Open-source Qwen2.5-7B model from qwen — available for download and self-hosting on Hugging Face.

Open-source Qwen2.5-1.5B-quantized.w8a8 model from redhatai — available for download and self-hosting on Hugging Face.

Open-source Kimi-K2.5-NVFP4 model from nvidia — available for download and self-hosting on Hugging Face.

Open-source pythia-70m-deduped model from eleutherai — available for download and self-hosting on Hugging Face.