Benchmarking Intelligence Efficiency of LM Inference
Pricing - Intelligence Per Watt
Benchmarking Intelligence Efficiency of LM Inference
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.
Intelligence Per Watt: A Study of Local Intelligence Efficiency
Jon Saad-Falcon*, Avanika Narayan*, John Hennessy, Azalia Mirhoseini, Chris Ré
Introducing Pipette: A benchmarking suite for on-device intelligence — Blog
Meet Pipette, an open-source platform for reproducible on-device AI benchmarks across models, quantization, runtimes and hardware.
High Performance AI Lab
High Performance AI Lab builds open inference systems and publishes the conditions behind every number — device, model, quant, and rep count.
Google for Developers Blog - News about Web, Mobile, AI and Cloud
Explore Gemma 3 270M, a compact, energy-efficient AI model for task-specific fine-tuning, offering strong instruction-following and production-ready quantization.
LLM Leaderboard - Comparison of over 100 AI models from OpenAI, Google, DeepSeek & others
Comparison and ranking the performance of over 100 AI models (LLMs) across key metrics including intelligence, price, performance and speed (output speed - tokens per second & latency - TTFT), context window & others.
Telepath's Sensemaking Computer Upends Personal Computing
Liquid AI on Twitter / X
Today, we release LFM2.5-350M. Agentic loops at 350M parameters.A 350M model trained for reliable data extraction and tool use, where models at this scale typically struggle.<500MB when quantized, built for environments where compute, memory, and latency are constrained.🧵 pic.twitter.com/zZPKzcCwH9— Liquid AI (@liquidai) March 31, 2026
Wafer - Ship the fastest inference in the world
Autonomous AI agents that profile, diagnose, and optimize GPU inference across your entire stack — from kernels to models to production pipelines.
The AI Engineering Report 2026: The AI Acceleration Whiplash - Ten Takeaways
What two years of telemetry data from 22,000 developers reveals about AI's real impact on developer productivity, code quality, and business risk in 2026.
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
Introducing Lumo 1.1 for faster, advanced reasoning | Proton
Lumo 1.1 is a faster, smarter AI assistant that matches Big Tech’s capabilities while protecting your privacy with zero-access encryption.
