Are you an AI builder, Join our OxBuild hackathon to showcase you skills

Join Now

Model Registry

Choose an open-source model and deploy it in seconds.

Models

38

Mistral-7B

Fast, efficient general-purpose language model for chat, summarization, and reasoning.

Llama-3.1-8B

Strong open-source model with excellent instruction following and reasoning quality.

Qwen 2.5-7B

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 - 33B

Specialized model for code generation, refactoring, and programming assistance.

Llama-3.3-70B

Large-scale model designed for complex reasoning and production-grade workloads.

Stable Diffusion 3.5 Large

High-resolution image generation model focused on output realism and detail.

YOLOv9

Real-time object detection model for images and video streams.

Whisper Large

High-accuracy transcription model suitable for production use cases.

Whisper Large v3

State-of-the-art multilingual speech-to-text model with improved accuracy, robustness, and performance for production transcription.

Qwen-3 32B

Large multilingual model built for strong reasoning and generation tasks.

GPT-OSS-20B

Open-source GPT-style model supporting both natural language and coding tasks.

GPT-OSS-120B

Premium open-source GPT-style large language model with top-tier reasoning, coding, and natural language capabilities for high-performance AI applications

DeepSeek R1 70B

Flagship reasoning model offering superior accuracy and deep problem-solving capabilities for demanding AI workloads.

DeepSeek R1 8B

Efficient reasoning-focused language model optimized for fast, cost-effective problem solving and structured AI tasks.

Kimi-K2-Thinking

Premium reasoning-optimized language model designed for deep thinking, complex problem solving, and advanced multi-step AI tasks.

BGE-Large

High-quality embedding model optimized for semantic search and RAG pipelines.

E5-Large

Embedding model optimized for similarity search and information retrieval.

Llama-3.2-3B

Lightweight model optimized for low-latency and cost-efficient workloads.

YOLOv11

Latest YOLO model offering improved object detection accuracy and performance.

Flux.1 Schnell

High-speed diffusion model optimized for rapid image generation.

Oxlo Image Pro

Premium image generation model delivering exceptional visual quality, precise prompt adherence, and reliable production-grade performance

Kokoro-82M

Lightweight speech synthesis model for generating natural-sounding audio.

Oxlo Image Ultra

Flagship image generation model optimized for ultra-realistic visuals and delivering exceptional photorealism.

Oxlo Coder Fast

High-speed code generation model designed for rapid completions, responsive coding workflows, and efficient developer productivity

DeepSeek V3.2

Powerful general-purpose language model delivering strong reasoning, coding, and natural language performance.

Llama 4 Maverick 17B

Efficient large language model designed for strong reasoning, conversational AI, and scalable production deployments.

DeepSeek V3 0324

Advanced language model optimized for complex reasoning, structured responses, and high-performance AI assistants.

Kimi K2.5

High-capacity reasoning model built for long context understanding, research workflows, and multi-step problem solving.

DeepSeek R1 0528

Reasoning focused language model specialized for analytical tasks, coding workflows, and complex multi-step reasoning.

Ministral 3 14B Instruct

Efficient instruction tuned language model designed for conversational AI, structured responses, and scalable production applications.

Qwen-3 Coder 30B

Code-focused language model for software development and technical reasoning.

Gemma-27B

Large language model focused on high-quality text generation and reasoning.

Gemma-3-4B

Compact model designed for efficient inference with solid generation quality.

Falcon 7B

Efficient language model optimized for fast, reliable text generation and general-purpose AI tasks.

Qwen 2.5 Coder 7B

Specialized code generation model designed for accurate coding assistance, debugging, and developer-focused workflows.

Falcon 11B

Advanced language model delivering enhanced reasoning, stronger text generation, and improved performance across diverse AI tasks