Model Registry
Choose an open-source model and deploy it in seconds.
Models
30
Mistral-7B
Fast, lightweight language model for chat, summaries, and basic reasoning.
Llama-3.1-8B
Strong open-source model with excellent instruction following and reasoning quality.
Qwen-7B
Multilingual language model optimized for general reasoning and conversational tasks.
Stable Diffusion v1.5
Widely used text-to-image model for fast and flexible image generation.
Whisper-Medium
Reliable speech recognition model for transcription and audio analysis.
DeepSeek Coder
Specialized model for code generation, refactoring, and programming assistance.
Llama-3.1-70B
Large-scale model designed for complex reasoning and production-grade workloads.
Stable Diffusion XL (SDXL)
High-resolution image generation model with improved realism and detail.
YOLOv8
Real-time object detection model for images and video streams.
Whisper Large
High-accuracy transcription model for long audio and noisy environments.
Whisper Large v3
High-accuracy transcription model for long audio and noisy environments.
Qwen-14B
Mid-sized model offering stronger reasoning and generation than smaller variants.
Mistral-24B
High-capacity model for advanced reasoning and longer context workloads.
Gemma-27B
Large language model focused on high-quality text generation and reasoning.
Qwen-32B
Large multilingual model built for strong reasoning and generation tasks.
GPT-OSS
Open-source large language models inspired by GPT-style conversational AI.
DeepSeek R1
Model optimized for structured reasoning and problem-solving workflows.
Kimi
Large-context language model designed for long documents and extended reasoning.
BGE-Large
High-quality embedding model optimized for semantic search and RAG pipelines.
E5-Large
Embedding model optimized for similarity search and information retrieval.
Gemma-3-4B
Compact model designed for efficient inference with solid generation quality.
Llama-3.2-3B
Lightweight model optimized for low-latency and cost-efficient workloads.
Llama-3-8B
General-purpose language model suitable for chat and content generation.
Llama-2-7B
Earlier-generation open-source model for basic language tasks.
Qwen-3 Coder
Code-focused language model for software development and technical reasoning.
YOLOv9
Latest YOLO model offering improved object detection accuracy and performance.
Kimi K2 VL
Multimodal model combining visual understanding with language reasoning.
Flux.1 Schnell
High-speed diffusion model optimized for rapid image generation.
Whisper-v3 Turbo
Optimized Whisper variant for faster transcription with lower latency.
Kokoro-82M
Lightweight speech synthesis model for generating natural-sounding audio.