Models

0tak1_v1 is a specialized text-to-image LoRA model built on FLUX.1-dev, offering custom image generation capabilities with specific trigger words.

Experimental AI model by unslothai hosted on HuggingFace, with minimal public documentation available. Further details pending release.

CausalLM 14B - State-of-the-art LLaMA2-compatible model with impressive multilingual capabilities, achieving top benchmarks scores and DPO version ranking #1 in ~13B category.

High-performing 14B parameter LLM with DPO training, achieving 7.62 on MT-Bench. Ranks #1 non-base model of its size on HuggingFace Open LLM Leaderboard.

A GGUF quantized version of Qwen2.5 14B model offering multiple quantization options (Q2-Q8) with file sizes ranging from 5.9GB to 15.8GB, optimized for different performance/quality tradeoffs.

16ch-VAE is an open-source VAE reproduction for SD3, offering high-quality image encoding with 31.5151 PSNR and improved performance over SD1.5/SDXL VAEs.

Experimental AI model '2' by unslothai, hosted on HuggingFace. Limited public information available. Appears to be a research-focused implementation.

A comprehensive collection of large language models (70B-120B parameters) quantized to 2-bit precision, optimizing storage while maintaining performance

A specialized AI model by Danrisi focused on generating 2000s-style aesthetic imagery, capturing the unique visual style of the millennium era.

Python-specific AI model from Jane Street with version compatibility requirements - use model_3_11.pt for Python 3.11+ or model.pt for earlier versions

A sophisticated 30B parameter LLM combining multiple LoRAs and model merges, optimized for storytelling and instruction-following with uncensored capabilities

A specialized LoRA model for black & white sketches, trained on 33 images with unique "333 Pro Sketch" trigger word. Optimized for 1280x832 resolution.

34b-beta is a powerful 34.4B parameter language model optimized for text generation with high MT-Bench scores and low contamination rates.

A powerful 35B parameter multilingual LLM based on Cohere's architecture, featuring 128K context, trained on 30M+ dialogue entries with enhanced fact-based capabilities.

A versatile text-to-image model merging ReVAnimated and Liberte Redmond, optimized for various styles including photorealistic, anime, and cartoon artwork.

A versatile 3D render-focused AI model capable of producing both realistic and cartoon-style images, with embedded VAE and dual-style capability.

A 3 billion parameter pretrained language model focused on German language processing, created by amuvarma and hosted on Hugging Face.

A specialized SDXL LoRA model focused on creating 3D rendered imagery, optimized for weights between 0.7-1.0 with recommended highres fix implementation.

A fine-tuned text-to-image model based on XenoGASM-MK2, specializing in artistic and versatile image generation with anime influences.

Large-scale LoRA model collection for Stable Diffusion XL with 98+ extracted models, optimized for text-to-image generation and featuring extensive documentation and technical specifications.

42-eicar-street by mcpotato is a specialized model hosted on HuggingFace, focusing on security testing and validation functionalities.

4x-Ultrasharp is an AI upscaling model designed for high-quality image enhancement, focusing on sharp detail preservation and 4x resolution scaling.

4x_NMKD-Siax_200k is an AI upscaling model designed for image super-resolution, offering 4x upscaling capabilities with NMKD architecture trained on 200k iterations.

4x upscaling AI model for image super-resolution, based on NMKD architecture. Trained for 178k steps. Developed by gemasai for high-quality image enhancement.