Running VLA Without a GPU: 1.6s to 230ms on a Qualcomm NPU

September 18, 2026

min read

Running VLA Without a GPU: 1.6s to 230ms on a Qualcomm NPU

More from Nota AI

Running VLA Without a GPU: 1.6s to 230ms on a Qualcomm NPU

September 18, 2026

min read

Running VLA Without a GPU: 1.6s to 230ms on a Qualcomm NPU

From Eight H100s to Two: The GPU Cost Savings of LLM Compression

August 26, 2026

min read

From Eight H100s to Two: The GPU Cost Savings of LLM Compression

Running Llama 8× Faster on a Raspberry Pi: The KCC 2026 On-Device AI Optimization Challenge

min read

Running Llama 8× Faster on a Raspberry Pi: The KCC 2026 On-Device AI Optimization Challenge

[NetsPresso® AQ Deep Dive] How to Quantize the K-EXAONE-236B Model to 4-Bit (NVFP4)

min read

[NetsPresso® AQ Deep Dive] How to Quantize the K-EXAONE-236B Model to 4-Bit (NVFP4)

Two papers discussing quantization methods specialized for MoE LLMs, accepted to an ICML 2026 workshop

min read

Two papers discussing quantization methods specialized for MoE LLMs, accepted to an ICML 2026 workshop

Full-Stack Optimization for Low-Light Video on Jetson Orin NX: From 400 ms to 28 ms

min read

Full-Stack Optimization for Low-Light Video on Jetson Orin NX: From 400 ms to 28 ms

The Real Reason TurboQuant Shook the Market: AI Optimization Has Gone Mainstream

min read

The Real Reason TurboQuant Shook the Market: AI Optimization Has Gone Mainstream

NotaMoEQuantization: An MoE-Specific Quantization Method for Solar-Open-100B

min read

NotaMoEQuantization: An MoE-Specific Quantization Method for Solar-Open-100B

ERGO: Efficient High-Resolution Visual Understanding for Vision-Language Models

February 26, 2026

min read

ERGO: Efficient High-Resolution Visual Understanding for Vision-Language Models

From Semi-Automatic to Fully Automatic: How NetsPresso Optimizes Models with an Agent

min read

From Semi-Automatic to Fully Automatic: How NetsPresso Optimizes Models with an Agent

[NetsPresso® x AI Agents] Easier to Use, Even More Powerful

min read

[NetsPresso® x AI Agents] Easier to Use, Even More Powerful

[Deep Dive: NetsPresso®] From Quantization to Graph Optimization: A Step-by-Step Model Deployment Pipeline

min read

[Deep Dive: NetsPresso®] From Quantization to Graph Optimization: A Step-by-Step Model Deployment Pipeline

[A Deep Dive into NetsPresso®] A Platform That Handles Everything from Model Optimization to Target Deployment

min read

[A Deep Dive into NetsPresso®] A Platform That Handles Everything from Model Optimization to Target Deployment

GenAI Everywhere: The Future of Edge AI Optimization with the New NetsPresso®

min read

GenAI Everywhere: The Future of Edge AI Optimization with the New NetsPresso®

Nota AI Joins AMD's Robotics Partner Network as the Only Korean Company

min read

Nota AI Joins AMD's Robotics Partner Network as the Only Korean Company

Smart Tech Korea (STK) 2026 Nota AI Booth Preview: Physical AI, Built at the Edge

min read

Smart Tech Korea (STK) 2026 Nota AI Booth Preview: Physical AI, Built at the Edge

Why Nota AI Became the Only Korean Company on the Panel at NVIDIA's APAC Partner Day: The Final Piece of Physical AI

min read

Why Nota AI Became the Only Korean Company on the Panel at NVIDIA's APAC Partner Day: The Final Piece of Physical AI

[NVIDIA Nemotron Hackathon] Grand Prize Among 20 Teams: Behind Two Sleepless Days

min read

[NVIDIA Nemotron Hackathon] Grand Prize Among 20 Teams: Behind Two Sleepless Days

[GTC 2026 Recap] The Trillion-Dollar Inference Race Begins: How Nota AI Fills the Gap

min read

[GTC 2026 Recap] The Trillion-Dollar Inference Race Begins: How Nota AI Fills the Gap

Beyond Model Optimization: Optimizing AI Agent Operations

August 31, 2026

min read

Beyond Model Optimization: Optimizing AI Agent Operations

How We Compress Large-Scale MoE Models

min read

How We Compress Large-Scale MoE Models

The Hardest Places to Run AI: Where Nota AI Tackles the Constraints

min read

The Hardest Places to Run AI: Where Nota AI Tackles the Constraints

Two Axes of MoE Quantization: How Nota AI Is Solving the Next Bottleneck in LLM Optimization

min read

Two Axes of MoE Quantization: How Nota AI Is Solving the Next Bottleneck in LLM Optimization

The Trillion-Dollar Inference Race Begins: How Nota AI Fills the Gap

min read

The Trillion-Dollar Inference Race Begins: How Nota AI Fills the Gap

Redefining Foundation Models for the Physical AI Era

min read

Redefining Foundation Models for the Physical AI Era

No items found.

What Six Months at Nota AI Looks Like

September 1, 2026

min read

What Six Months at Nota AI Looks Like

The Person Watching From the Farthest Seat, and the Closest

November 20, 2025

min read

The Person Watching From the Farthest Seat, and the Closest

A Time That Made Me Think Beyond Technology, Toward Product

November 20, 2025

min read

A Time That Made Me Think Beyond Technology, Toward Product

Wanting to Show 'Uncle's Workplace'

November 20, 2025

min read

Wanting to Show 'Uncle's Workplace'

The Designer Who Made Nota AI Visible

November 19, 2025

min read

The Designer Who Made Nota AI Visible

Shaped Nota AI's Last Six Years

November 19, 2025

min read

Shaped Nota AI's Last Six Years

Nota AI's Signature Recipe

August 24, 2026

min read

Nota AI's Signature Recipe

Trying Something New at KCC and ICML

August 21, 2026

min read

Trying Something New at KCC and ICML

Where We Make AI Everywhere

min read

Where We Make AI Everywhere

Nosik’s Diary - My First Day at Nota AI

min read

Nosik’s Diary - My First Day at Nota AI

Safeguarding Roads and Industrial Sites

min read

Safeguarding Roads and Industrial Sites

Goodbye 2024, Hello 2025!

February 6, 2025

min read

Goodbye 2024, Hello 2025!

Nota AI to Optimize On-Device AI for Humanoid Robots, Connecting LG Electronics’ Robot Platform with Mobilint’s NPU

September 8, 2026

Nota AI to Optimize On-Device AI for Humanoid Robots, Connecting LG Electronics’ Robot Platform with Mobilint’s NPU

Nota AI Joins ‘AI for Everyone’ Following National Foundation Model Project, Expanding Optimization from National AI Models to Services for Everyday Use

September 1, 2026

Nota AI Joins ‘AI for Everyone’ Following National Foundation Model Project, Expanding Optimization from National AI Models to Services for Everyday Use

Nota AI’s Optimization Research Earns Global Recognition Two Papers Accepted at EMNLP 2026, a Leading NLP Conference

August 25, 2026

Nota AI’s Optimization Research Earns Global Recognition Two Papers Accepted at EMNLP 2026, a Leading NLP Conference

Nota AI Advances to Round 3 of Korea's Sovereign AI Foundation Model Project Alongside Upstage

August 20, 2026

Nota AI Advances to Round 3 of Korea's Sovereign AI Foundation Model Project Alongside Upstage

Nota AI Expands AI Optimization Business, Enters "AI Agent Operations Optimization" Market to Secure New Growth Driver

August 14, 2026

Nota AI Expands AI Optimization Business, Enters "AI Agent Operations Optimization" Market to Secure New Growth Driver

"Beyond AI Models, Toward Optimized AI Agent Operations" Nota AI Signs First Commercial Project Agreement with MetaM, a Leading AICC Provider

August 13, 2026

"Beyond AI Models, Toward Optimized AI Agent Operations" Nota AI Signs First Commercial Project Agreement with MetaM, a Leading AICC Provider

Thank you! Your submission has been received!

Oops! Something went wrong while submitting the form.

Nota AI, On the Edge

Watch video ›

Watch video ›

Watch video ›

Watch video ›