local.ai — Charting the transition from cloud AI to local AI.

Alex Cheema on Twitter / X

This is why we need open benchmarks for local AI.Otherwise it turns into tribalism and name calling.We will be publishing the largest database of open benchmarks for local AI, tested on 1,000+ real hardware setups. Every device, every interconnect, different… https://t.co/ZsU3PCdSsZ— Alex Cheema (@alexocheema) March 9, 2026

Together AI | The AI Native Cloud

Build what's next on the AI Native Cloud. Full-stack AI platform for inference, fine-tuning, and GPU clusters — powered by cutting-edge research.

AI-Native Cloud | DigitalOcean

Run AI products in production with a unified stack for agents, inference, and cloud—built for control, performance, and economics at scale.

Coasts — Containerized Hosts for AI Agents

Free, open source parallel runtimes for AI agents. Run multiple isolated environments on your machine — no cloud, no conflicts.

Cloudflare Workers AI | Open-source AI inference

Workers AI facilitates the scalable development & deployment of AI applications at the edge.

Local-First AI Inference: A Cloud Architecture Pattern for Cost-Effective Document Processing

The Local-First AI Inference pattern routes 70–80% of documents to deterministic local extraction at zero API cost, reserving Azure OpenAI calls for edge cases and flagging low-confidence results for human review. Deployed on 4,700 engineering drawing PDFs, it cut API costs by 75% and processing time by 55%, while bounding errors through a human review tier.

Nativ — Local AI for your Mac

Frontier intelligence on your desk. No accounts, subscriptions, or cloud.

Locally AI - Run AI models locally on your iPhone, iPad, and Mac.

Run Llama, Gemma, Qwen, DeepSeek, and more on your iPhone, iPad, and Mac. Optimized for Apple Silicon. Offline. Private.

AI Model & API Providers Analysis | Artificial Analysis

Comparison and analysis of AI models and API hosting providers. Independent benchmarks across key performance metrics including quality, price, output speed & latency.

How to Build an AI Data Center | IFP

Part One of Compute in America: Building the Next Generation of AI Infrastructure at Home

Where are the local AI apps?

Millions build AI apps with natural language, but local AI deployment remains  complex. Why?

Intelligence per Watt: Measuring Intelligence Efficiency of Local AI

Large language model (LLM) queries are predominantly processed by frontier models in centralized cloud infrastructure. Demand growth strains this paradigm faster than providers can scale. Two advances create an opportunity to rethink it: small, local LMs (<=20B active parameters) now achieve competitive performance to frontier models on many tasks, and local accelerators (e.g., Apple M4 Max) can host these models at interactive latencies. This raises the question: can local inference viably redistribute demand from centralized infrastructure? This requires measuring both whether local LMs can accurately answer real-world queries and whether they can do so efficiently on power-constrained devices (e.g., laptops). We propose intelligence per watt (IPW), task accuracy per unit of power, as a unified metric for the capability and efficiency of local inference across model-accelerator configurations. We evaluate 20+ state-of-the-art local LMs, 8 hardware accelerators (local and cloud), and 1M real-world single-turn chat and reasoning queries. For each query, we measure accuracy (local LM win rate against frontier models), energy, latency, and power. We find three key results. First, local LMs successfully answer 88.7% of these queries, with accuracy varying by domain. Second, longitudinal analysis from 2023-2025 shows IPW improved 5.3x, driven by both algorithmic and accelerator advances, with locally-serviceable query coverage rising from 23.2% to 71.3%. Third, local accelerators achieve at least 1.4x lower IPW than cloud accelerators running identical models, revealing significant headroom for local accelerator optimization. These findings demonstrate that local inference can meaningfully redistribute demand from centralized infrastructure for a substantial subset of queries, with IPW serving as the critical metric for tracking this transition.

raullenchai/Rapid-MLX

The fastest local AI engine for Apple Silicon. 4.2x faster than Ollama, 0.08s cached TTFT, 100% tool calling. 17 tool parsers, prompt cache, reasoning separation, cloud routing. Drop-in OpenAI replacement. Works with Claude Code, Cursor, Aider.

raullenchai/Rapid-MLX

The fastest local AI engine for Apple Silicon. 4.2x faster than Ollama, 0.08s cached TTFT, 100% tool calling. 17 tool parsers, prompt cache, reasoning separation, cloud routing. Drop-in OpenAI replacement. Works with Claude Code, Cursor, Aider.