Local AI Models

Local AI Models Enhances API Security with New Authentication Middleware

New API authentication middleware supporting API keys and JWTs has been released for enhanced security.

Local AI Models Introduces Advanced Quantization Options for Reduced Memory Footprint

Local AI Models now offers advanced 4-bit and 2-bit quantization to reduce model memory requirements.

Local AI Models Releases Beta API for Fine-Tuning Custom Models

Local AI Models Enhances Performance with New Quantization Techniques

Local AI Models introduces new quantization techniques to boost on-device model performance and reduce resource consumption.

New API Endpoints for Model Management and Monitoring Available in Local AI Models

Local AI Models Introduces Enhanced Quantization Techniques for Faster Inference

Local AI Models now supports advanced quantization methods for faster, more efficient local AI model inference.

Local AI Models Introduces Expanded API for Real-time Embeddings

Local AI Models has launched a new API endpoint for real-time text embedding generation.

Local AI Models Enhances Performance with Quantization Support

Local AI Models now supports model quantization, improving performance and reducing memory usage for local deployments.

API Endpoint for Real-time Text Generation Now More Robust

Local AI Models has updated its real-time text generation API endpoint for increased stability and lower latency.

Local AI Models Introduces Enhanced Quantization Support for LLMs

Local AI Models now offers improved quantization features for running LLMs efficiently on limited hardware.

New API Endpoint for Real-time Data Streaming Now Available in Local AI Models

Local AI Models Enhances Performance with Optimized Quantization Techniques

Local AI Models has boosted performance through new optimized quantization techniques for on-device models.

New API Endpoints for Image Generation Models Released by Local AI Models

Local AI Models introduces new API endpoints for enhanced control and batch processing of its image generation models.

Local AI Models Enhances Performance with Quantization Updates

Local AI Models has improved inference speed and reduced memory usage through updated quantization techniques.

New API Endpoint for Model Fine-tuning Available in Local AI Models

Local AI Models has launched a new API endpoint enabling developers to fine-tune models locally.

Local AI Models Introduces Quantization Support for Faster Inference

Local AI Models now supports quantization for faster and more memory-efficient model inference.

Security Update Addresses Potential Vulnerability in Model Loading

An urgent security update has been released to fix a potential vulnerability in the model loading process; users should update immediately.

Local AI Models Introduces Advanced Fine-Tuning Capabilities

Local AI Models now offers enhanced fine-tuning options for open-source language models, allowing for greater customization with user datasets.

New API for Real-time Text Generation Available in Local AI Models

Local AI Models introduces a new API endpoint for optimized, low-latency real-time text generation.

Local AI Models Enhances Performance with New Quantization Techniques

Local AI Models now offers faster inference and lower memory usage with new automatic quantization features.

Local AI Models API v2.1 Released with Enhanced Streaming and Error Handling

Local AI Models API v2.1 improves real-time streaming and provides more detailed error handling for developers.

Local AI Models Introduces Advanced Quantization Techniques for Faster Inference

Local AI Models now offers advanced quantization techniques to speed up model inference and reduce resource requirements.

New API Endpoint for Asynchronous Task Processing Now Available

Local AI Models now offers a new API endpoint for handling asynchronous AI tasks, improving scalability.

Local AI Models Introduces Enhanced Quantization for Faster Inference

Local AI Models has rolled out enhanced quantization methods to boost inference speed and reduce model size.

Ollama 0.6 Released: Multi-GPU Support and Faster Model Switching

Ollama 0.6 adds multi-GPU support, instant model switching, and AMD ROCm compatibility.