Blog

Clarifai and Nebius

The Next Chapter: Clarifai Compute Orchestration and Reasoning Engine Joins Nebius
Today, we are thrilled to announce a monumental milestone in Clarifai’s journey: we have entered into an agreement for Nebius (NASDAQ: NBIS), the AI cloud company, to license our core engineering a...
May 19, 2026 - Matthew Zeiler, Ph.D. Founder and CEO, Clarifai

NVIDIA Nemotron 3 Nano Omni on Clarifai Reasoning Engine: Zero Day Support at 400 Tokens Per Second

We’re excited to announce day-0 support for NVIDIA Nemotron 3 Nano Omni on Clarifai. Available now on Clarifai Reasoning Engine.
April 28, 2026 - Clarifai

Clarifai 12.3: Introducing KV Cache-Aware Routing

This blog post focuses on new features and improvements. For a comprehensive list, including bug fixes, please see the release notes.
April 9, 2026 - Clarifai

Run Gemma 4 Locally Deploy Frontier AI on Your Hardware with Public API Access

When you want to run frontier models locally, you hit the same constraints repeatedly.
April 7, 2026 - Clarifai

What is Kimi K2.5 Architecture Benchmarks AI Infra Guide

Open‑weight models are rapidly narrowing the gap with closed commercial systems. As of early 2026, Moonshot AI’s Kimi K2.5 is the flagship of this trend: a **one‑trillion parameter Mixture‑...
March 18, 2026 - Clarifai

ilama.cpp

Local large‑language‑model (LLM) inference has become one of the most exciting frontiers in AI. As of 2026, powerful consumer GPUs such as NVIDIA’s RTX 5090 and Apple’s M4 Ultra enable **state‑of‑t...
March 17, 2026 - Clarifai

Clarifai Reasoning Engine Achieves 414 Tokens Per Second on Kimi K2.5

Using custom CUDA kernels and speculative decoding optimized for reasoning workloads, we achieved 414 tokens per second throughput on Kimi K2.5 running on Nvidia B200 GPUs, making us one of the fir...
March 16, 2026 - Clarifai

Flash Attention 2

The transformer revolution is now deep into its long‑context era. Models like GPT‑4 (32 k tokens), MosaicML’s MPT (65 k), and Claude (100 k) can process entire chapters or codebases. Yet as con...
March 16, 2026 - Clarifai

Clarifai 12.2: Three-Command CLI Workflow for Model Deployment

This blog post focuses on new features and improvements. For a comprehensive list, including bug fixes, please see the release notes.
March 12, 2026 - Clarifai

Clarifai vs Other Inference Providers

The AI landscape of 2026 is defined less by model training and more by how effectively we serve those models. The industry has learned that inference—the act of deploying a pre‑trained model—is...
March 10, 2026 - Clarifai

What is LPU

The AI hardware landscape is shifting rapidly. Five years ago, GPUs dominated every conversation about AI acceleration. Today, agentic AI, real‑time chatbots and massively scaled reasoning systems ...
March 10, 2026 - Clarifai

Optimized Inference in the Age of Open Source Innovation

The recent release of DeepSeek's R1 model, a groundbreaking open-source model from the Chinese AI startup, has sparked a wave of excitement in the AI community. What ma...
January 27, 2025 - Clarifai

Nvidia's Breakthrough and Hybrid AI with Clarifai

In the ever-evolving landscape of technology, there are moments that redefine our expectations and propel us toward new horizons. This week at NVIDIA’s Keynote at their GTC conference we stand at a...
March 19, 2024 - Chris Kent

Retail Solutions: AI Solutions for Smart Shelves

I'm old enough to remember a time when stores had little price tags stuck on all their products, and they were often the deciding factor in what people would pay for them. You'd bring the item you ...
April 4, 2022 - Ian Kelk

What Is Edge Computing in AI?

Back in 2017, Apple announced the iPhone X with its A11 Bionic chip—a system‑on‑a‑chip (SoC) containing a dedicated “neural engine” for face and speech recognition. Since then, every iPhone inc...
September 13, 2021 - Ian Kelk

All You Need to Know about Software 2.0

Ten years ago, engineer and investor Marc Andreessen wrote in his now-famous article in the Wall Street Journal that "software is eating the world." These days industry visionaries are predicting a...
August 31, 2021 - Jeff Toffoli

Applications of Computer Vision in Healthcare

Computer vision and machine learning models are designed to recognize, understand images and data to execute actions that only humans were once thought...
December 16, 2019 - Anand Butani

Introducing Clarifai’s New Apparel Detector Model

In 2017, we created our first apparel classification model to help retailers streamline their [workflow using tools like automa...
November 20, 2019 - Kia Edwards

How Online Retailers Are Using Deep Learning to Grow Their Business

The growth of Artificial Intelligence (AI) has introduced many amazing new technologies, and a deluge of virtual features, particularly in the field of mach...
September 9, 2019 - Anand Butani

Machine Learning For The Movies

For many, machine learning is useful only insomuch that the insights it generates drive business or cut costs. Within the film industry, top studios have traditionally banked huge budgets on new sc...
August 22, 2019 - Daniel McNeela

4 Ways AI is Improving Retail Merchandising Efficiencies

Artificial intelligence in its many forms is showing a huge impact on the retail industry. Today, this technology is already empowering merchandisers to tail...
January 14, 2019 - Monica Watson

3 Ways AI-Powered Security Cameras Can Help Improve Customer Service

You’ve seen them. Today, [most brick and mortar retailers rely on security cameras in stores to protect them from theft and other crimes](/blog/announcing-clarifai-and-boulder-ais-strategic-allianc... November 28, 2018 - Natalie Fletcher