Sitemap

October 14, 2026

All English articles on this site, newest first within each category.

Local AI

• What Is Strata? How a 12GB GPU Runs a 125B Model: Mechanism, Speed, and Supported Setups
• Is Waiting for a Long Text Proportional to Its Length? I Measured Time to First Token in Seven Steps of Input
• Models Installed With Ollama Won’t Load in llama.cpp? The Seven That Failed, and Re-measuring From Hugging Face
• Can Moving 3D Gaussian Splatting Be Streamed by Sending Only What Changes? Formats and Real Uses of 4DGS Delivery
• What Runs on a Phone or in an App? 23 Small Generative AI Models Compared on Smartness, Speed and Size
• I Want to Look at 3DGS: Free Viewers on the Web, Phone, Steam and Quest, Compared
• Slower Despite the Name “Lightning"? I Measured the New and Old Nemotron Side by Side
• DGX Spark Gets a 64GB Version and the 128GB Rises to $6,950: What Fits in Half the Memory, Checked Against EVO-X2 Measurements
• Does Qwen3.8-Flash-Next, a Qwen4 Preview, Run at Home? I Measured the 2-bit Version on an RTX 5060 Ti and RTX 3060
• How to Put a Small AI in a Device: Small LLMs on Phones, Embedded Boards and Tiny Hardware, and the Parts They Need
• Which Local LLM to Install First in 2026: Picks by VRAM and Use, From Measured Numbers
• How Many GB Does DeepSeek V4.1-Flash Need to Run? — I Checked Every Quantization Being Distributed
• Too Many New AI Models, Can’t Tell Which Is Which? — I Sorted the Latest 17 by Size, Design, and Use
• A Local LLM on Par with Opus 5? I Tried MiMo-V2.6 — the Big One Ran Too, With Multiple GPUs
• DeepSeek V4.1-Flash Won’t Run — I Tried to Get It Working Locally
• Want to Type Long Text on the iPhone Duo? — I Looked Into 6 Japanese-Layout Mobile Keyboards
• Two Cards in the Same PC — How Far Apart Are They? RX 9060 XT vs RTX 3090 on Speed and Power Cost (Part 2 of the RX 9060 XT Series)
• How Much Better Is Ornith 1.5? — I Measured 1.0 and 1.5 With Three Yardsticks
• Can One Photo Become a 3D Model? — Canon’s Dual Pixel 3D and How Other Methods Compare
• Can a Local Model Reproduce Jev, the Fast-Decision AI? — Rebuilding the Mechanism on My Own GPU
• What Runs on 8GB? I Measured 22 Local LLMs and Sorted Them by Memory Tier
• Are the New iPhone 18 Pro / Pro Max / Duo Really 2x for AI? What Matters If You Run Your Own Local Model
• Where Do You Start With GPT-6 Astra? Entry Points, Pricing, and What to Decide Before You Automate
• How Far Can You Automate Your PC With Generative AI? — Comparing GPT-6 Astra and Claude Using the Official Documentation
• My Eyes Started Hurting From Reading Long AI Answers — E-Paper Cuts the Strain
• Does a 15GB Model Fit? First Things to Decide When Running Local LLMs on a Radeon RX 9060 XT (Part 1 of the RX 9060 XT Series)
• Steam Frame — What It Gave Up, and What It Kept: Comparing the Specs Against the Major Headsets
• I Want to Enjoy VR on Ubuntu Too! — Checking Whether a PC I Use as My Local-AI Server Can Also Run VR
• Running Out of Room for Models — I Checked SSD Prices and Found Something I Should Have Looked at First
• How Do You Actually Choose a Local LLM Model? Five Axes I Found by Running a Dozen of Them — Tuning Series, Part 1
• How Long Until the First Output Appears? — I Measured the Initial Wait Time of a Local LLM
• Can My Local AI Be Reached from the Outside? — I Checked Whether the PC Running Ollama Is Safe
• Four Mini PCs Combine Into One? Lenovo’s ThinkCentre X Ultra Doesn’t Say How
• A Third 128GB Mini PC? NVIDIA’s RTX Spark Leaves Out the One Number That Decides Local LLM Speed
• Have E-Paper Phones Become Practical Enough to Use? A Look at the Hisense A10 Ultra and the Current BOOX and Bigme Lineup
• Apple Says 4.3x AI Performance. Which Half of a Local LLM Does That Touch?
• A Mac You Can Put 512GB Into — What Changes, Seen From a 16GB Wall
• Video Generation Times That Would Not Settle on a Single RTX 3090
• What Actually Changed in Claude Fable 5.1 — And What Using It Commits You To
• Will a Pixel 11 Run a Model I Brought Myself? — What the 3.5x Claim Does Not Cover
• ComfyUI Said the Render Took 5 Seconds — Two Reasons the Number Was Not Real
• RAM Is Expensive — Can an SSD Stand In? Checking the Latency and the Lifespan
• Do Grouped Disks Actually Go Faster? RAID, and What Is Inside an SSD
• Every VR Headset From DK1 to Quest 3S — What Actually Changed in Twelve Years
• My SSD Filled Up — Rethinking Where Data Goes, by Price and by Speed
• Does an External GPU Make a Mini PC Stronger? Past 16GB the Roles Swapped
• Can an E-Paper Second Screen Handle Writing Work? What Six Years Changed
• My External GPU Ran at 1/25 the Speed of the Integrated One – Changing the Cable Made It 36x Faster
• I Said External GPUs Do Not Work Over Thunderbolt. Then One Did — The Cause Was My Own Leftover Setting
• Do Identical Settings Give an Identical Picture? Five Styles, Two Cards, Compared
• Running Local LLMs on 128GB of Memory — GMKtec EVO-X2, Mac Studio and DGX Spark Compared
• Image Generation on an Arc B580 vs an RTX 3090 — Same Picture, Measured for Speed and Power
• Does Image Generation Run on an Intel Arc B580? Trying It Without Touching the Host
• Point It at a Local Model and Nothing Leaves? — I Read the Published Grok Build Source
• Parsing Web Pages: Sending the Whole Thing to an LLM Gets Expensive — I Measured What Moving It Local Saved
• I Set It, So Why Is Nothing Happening? — The KV Cache Compression That Was Being Ignored
• I Thought Three Mini PCs Used This Chip — Searching Differently Found Fourteen, Including a NAS and a Laptop
• Buying an SSD Now That Prices Have Climbed — What Sets the Price and the Lifespan
• The Empty Air Duster Cans Piled Up — I Switched to Electric, and Got a Battery Lifespan With It
• GPU Prices Went Up Again — Where Does Buying Stop Making Sense and Renting Start?
• There Were Two Keyboards on My Desk — I Compared Seven Best-Selling KVM Switches Before Choosing
• I Got Rid of the eGPU Enclosure I Recommended Seven Years Ago — So Which One Would I Buy Now?
• Can You Keep MCP Entirely on Your Own Machine? I Counted 2,500 Servers | MCP Part 3
• Are There Really Over 9,000 MCP Servers? Sorting Them by What You Actually Want to Do | MCP Part 2
• What Is MCP? Why Can’t an AI Just Read a File on My Own Machine? | MCP Part 1
• Thirty Minutes on My Own Machine — What Would Renting a GPU Have Cost?
• Running a 235B Model on a Mini PC — The Settings Traps on the GMKtec EVO-X2
• Can You Move an Avatar Face Without a Headset? It Turned Out to Cost Nothing
• Local AI Speed Is Decided by Memory Bandwidth — Four Machines Measured
• Trying Ornith-1.0 on Home Hardware — Measuring Speed and How Well It Reasons
• OCuLink or Thunderbolt for an External GPU? I Measured Both With the Same Card | Mini PC eGPU Part 1
• The Mini PC Lid Would Not Close — I Tried Three M.2-to-OCuLink Adapters
• I Want My Avatar to Emote While Wearing the Headset — What Do I Actually Buy for Face Tracking?
• What the Intel Arc B580 Could and Could Not Do | Intel Arc B580 Local LLM Part 7
• What Happens If You Mix GPUs From Different Vendors? RTX 3090 + Intel Arc B580 Measured | Intel Arc B580 Local LLM Part 6
• Six Local LLMs, Same Prompts: Speed, Japanese Output, Summarizing and Code
• My Whole Local AI Workstation, Documented: Ubuntu + RTX 3090 + Ollama + ComfyUI
• What Are AI Agents, Really? Four Types and Which Ones Run Locally (June 2026)
• My External GPU Would Not Run Over Thunderbolt — Three GPU Generations Tested | Intel Arc B580 Local LLM Part 5
• Why Did Full-Body VR Trackers Start Adding Cameras? The 2026 Move to Hybrids
• From GPT-2 to Kimi K3: What Actually Changed in Seven Years? A Beginner-Friendly Walkthrough
• Qwen3:14b Fits in 12GB — So Why Does It Keep Getting Slower? | Intel Arc B580 Local LLM Part 4
• AMD Published Everything About This Model — So Could I Train It Myself? Instella-MoE on a Mini PC
• How Fast Are Models That Fit in 12GB? Speed and Power Measured | Intel Arc B580 Local LLM Part 3
• My Arc B580 Reported PCIe 1.0 x1 — It Was Not Broken | Intel Arc B580 Local LLM Part 2
• Intel Arc B580 Feels Slow for Local LLMs? A Mesa Update Made It 3.3x Faster | Intel Arc B580 Local LLM Part 1
• What Does Kimi K3 Actually Cost? Frontier Model Pricing Compared
• Background Removal, Upscaling, img2img and Inpainting in ComfyUI: Four Workflows That Run Locally for Free
• Power-Limiting Your GPU for Local LLMs: 9% Less Power for 2% Less Speed
• Local LLM Load Times Measured on 3 Machines: The Culprit Is the SSD — and the Memory Wall
• Which Local LLM Is Best for Coding? 7 Models Measured Head-to-Head (July 2026, 24GB Edition)
• EVO-X3 vs EVO-X2: What Actually Differs — Reading the Pre-Launch Specs as an X2 Owner
• Running an RTX 5060 Ti on the GMKtec EVO-X2 Mini PC via OCuLink (eGPU)
• Where Local AI Really Shines: Privacy, Offline, and Big Batch Jobs
• What to Buy for Local AI: Dedicated GPU vs Mac vs High-Memory Mini PC
• Is Bigger Smarter? Testing Local LLM Reasoning with 8 Puzzles on the GMKtec EVO-X2
• Gemma 4 Speed by Quantization: Same Model, Several-Fold Difference (and the Quant That Won’t Fit)
• The Family Tree of Open-Source LLMs: 8 Major Families
• 5 Local LLMs Benchmarked at Home: 31B to 235B (2026)
• Gemma 4 Quantization Compared: Q4 vs QAT vs Q8 (Speed & Quality)
• Gemma 4 vs Qwen 3.6: Which Should You Run on Your GPU?
• ComfyUI for Beginners: From Install to Your First Image (2026)
• AI Runs on Your Phone Now: Gemma 4 Edge, BitNet and LiteRT-LM
• Does Repasting Your CPU Actually Lower Temps? I Measured It
• How Much Does a GPU Cost to Run? Power Draw and Monthly Electricity
• Power, Cooling and Noise for Local-AI GPUs: Running 300W+ Cards Stably
• One GPU for VR, AI and Image Generation? Picking by Use-Case Mix (2026)
• I Want to Generate AI Images: Where’s the Sweet Spot for Value?
• NVIDIA vs AMD vs Intel: Which GPU Should You Actually Buy? (2026)
• Dual-GPU Local AI: Running RTX 3090 + RTX 3060 Together
• 2026 GPU Spec List for Local AI, VR and Image Generation
• Starting Local AI with a Used GPU: The Value of the RTX 30/40 Series
• Running a Local AI Chatbot at Home: A Budget-by-Budget Guide
• Getting Started with Ollama: Run a Local AI Chatbot in 10 Minutes
• Running huge LLMs (235B, 745B) on consumer & mini-PC hardware — hands-on

VR

• Which PC Webcam Should You Buy? Four Types Compared: Fixed, Wide-Angle, AI-Tracking and Auto-Framing
• Can One Camera Move an Avatar’s Whole Body? What the Free Software HIROMEIRO Does, From Its Manual and Source
• Sweat and Smell in a VR Headset — What I Found Looking Into Replacement Face Covers
• Full-Body Tracking in VRChat — Everything From Zero to Moving, Researched
• Body and Face Tracking in VR, 2026 — How Far It Has Actually Come

Others

• Want to Make AI Images? Which Should You Try First — A Year’s Worth of New Software and Services, Researched
• Want to Add a Second Camera? — Why HDMI Output and Remote Control Would Not Coexist
• Every Pair of AR Glasses From Google Glass to 2026 — And What Changed
• Video Can Be Generated Locally Too? Looking Into Wan 2.2, LTX-2 and FramePack
• RAM Prices Went Up Again — Should I Buy Another Graphics Card Now?
• Is a Whole Mini PC Really Cheaper Than the RAM Alone? Checking the 2026 Mini PC Market
• How to Help After the 2026 Kumamoto Earthquake From Outside Japan

3D & Printing

• Keeping Filament Dry — What a Dry Box Actually Does, and How to Choose One
• Can You Turn a Moving Person Into 3D Video? — What 4D Gaussian Splatting Actually Needs
• Can You Build a 3D Model From Phone Photos? — Getting Started With Photogrammetry

PC Benchmarks

• I Bought a GALLERIA XA7C-R37 — Core i7-11700 / 16GB / RTX3070
• Lenovo Legion 550Pi (GTX 1650): An Entry-Level Gaming Laptop, Put Through VR
• Lenovo Legion 550Pi (RTX 2060): An Entry-Level Gaming Laptop That Actually Handles VR
• DELL G5 5505 Review: An All-AMD Gaming Laptop (Ryzen 7 4800H / 16GB / Radeon RX 5600M), Tested in VR
• Oculus Rift S Price Drop: Rechecking How Light It Really Is on Your GPU
• Lenovo Legion Y740 (15) Review: A High-End 15-Inch Gaming Laptop, Tested in VR
• Driving a Pimax 8K Plus with an ASUS VivoBook S15 Ultrabook + eGPU (RTX 3060 Ti)
• Driving a Vive Cosmos Elite from an ASUS VivoBook S15 Ultrabook with an eGPU (RTX 3060 Ti)
• Driving an Oculus Quest 2 from an ASUS VivoBook S15 Ultrabook with an eGPU (RTX 3060 Ti)
• Driving the Original Oculus Quest from an ASUS VivoBook S15 Ultrabook with an eGPU (RTX 3060 Ti)
• Driving an Oculus Rift S from an ASUS VivoBook S15 Ultrabook with an eGPU (RTX 3060 Ti)
• Attaching an eGPU (RTX 3060 Ti) to the ASUS VivoBook S15 Ultrabook, and Putting VR to the Test
• GALLERIA RM5R-G60S Review: A Budget Mini-Tower Gaming PC (Ryzen 5 3500 / GTX 1660 SUPER), Tested in VR