Local Inference
On-prem and on-device model serving, private inference, sovereignty.
Monthly frequency: 2026-05: 1 · 2026-06: 6 · 2026-07: 4 · 2026-08: 11 · 2026-09: 9 · 2026-10: 17
Deepseek crushed everyone — Matthew Berman2026-10-28
Kimi K3.1 Passes the Rubik's Cube Test — Matthew Berman2026-10-25
Podcast: Kimi K3.1 Pro, the new cyber reality, and Muse musings — Nathan Lambert2026-10-25
Introducing Kimi K3.1 Pro — Simon Willison2026-10-23
Team AMA (and Kimi K3.1 Testing!!) — Matthew Berman2026-10-23
Who is local AI really for? — Matthew Berman2026-10-23
Why AI Compute Comes in Rectangles — Erik Bernhardsson, Modal — Latent Space2026-10-22
The Huawei-DeepSeek Symbiosis — SemiAnalysis2026-10-21
Latest open artifacts (#25): DeepSeek V4.1 Flash 1017, American-made models, and new regulatory controls in the US & China — Nathan Lambert2026-10-20
Mac Mini For AI Agents: How Much Memory You Need, And How To Use What You Have. — Nate B. Jones2026-10-20
The Programmable Data Center — Evan Conrad, SF Compute — Latent Space2026-10-20
How DeepSeek Uses Less Memory — Matthew Berman2026-10-18
Meta shakes up the frontiers, open and closed — Nathan Lambert2026-10-17
Robots That Predict the Future: Dyna-2 & Physical AI — Jason Ma, Dyna Robotics — Latent Space2026-10-13
Mistral is BACK! (Le Chonk) — Matthew Berman2026-10-07
Introducing Mistral Large 4: Le chonk — Simon Willison2026-10-06
Qwen3.8 27B addition in words — Simon Willison2026-10-04
2026 in LLMs (so far) — Simon Willison2026-09-27
NVIDIA PAIR Connects Your Computers for Local AI — Matthew Berman2026-09-18
A Worm With 302 Neurons Inspired Their Architecture — Ramin Hasani, Liquid AI — Latent Space2026-09-18
Engrams Embedding Entendre: Codesign for Efficient DRAM/SSD Offloading — SemiAnalysis2026-09-18
Intelligence is Everywhere: Why the AI 'Race' is Already Over — Nate B. Jones2026-09-14
A Brain Too Big to Carry — On-Device vs Datacenter Inference — SemiAnalysis2026-09-14
Sam Altman and Apple's New CEO are Fighting Over One Thing. It's Not What You Think. — Nate B. Jones2026-09-14
Deepseek did it again... — Matthew Berman2026-09-11
Where Does a Robot Think – On-Device vs Datacenter Inference — SemiAnalysis2026-09-09
Apple's New Mac Line is Built Around Local AI. The Bet Is You'd Rather Own Than Rent. — Nate B. Jones2026-08-31
Introducing Hy4 Preview — Simon Willison2026-08-29
Cancel your subscriptions, Ox-Alpha is here! (GLM 5.3 Flash) — Matthew Berman2026-08-29
AI will have infinite speed, your computer will not — Matthew Berman2026-08-28
This feels illegal... — Matthew Berman2026-08-27
Qwen3.8-Flash-Next — Simon Willison2026-08-26
The Most Important Chart In AI Right Now — Matthew Berman2026-08-26
Your Mac can get a job — Matthew Berman2026-08-25
6 Open-Source AI Projects Trending NOW — Matthew Berman2026-08-17
Open-source is WINNING — Matthew Berman2026-08-04
Leopold Aschenbrenner's Warning Signal Apple Completely Missed — Nate B. Jones2026-08-03
China's K3 Model Reveals the Problem With Open Weights — Nate B. Jones2026-07-20
I Cut the Internet and Let AI Read the File I Could Never Upload. It Caught the Leak. — Nate B. Jones2026-07-19
Kimi K3 just beat FABLE. — Matthew Berman2026-07-17
Deepseek ban? — Matthew Berman2026-07-15
Apple just raised prices... — Matthew Berman2026-06-27
I can't believe this happened... — Matthew Berman2026-06-26
You NEED to try these 12 open-source AI projects RIGHT NOW — Matthew Berman2026-06-24
Apple’s Worst Nightmare #apple #google #gemini — Nate B. Jones2026-06-19
The 3 Biggest WWDC Headlines You Missed #wwdc #apple #tech — Nate B. Jones2026-06-16
Apple WWDC 2026: The AI Story Everyone is Missing — Nate B. Jones2026-06-11
Self Improving AI actually solves everything — Matthew Berman2026-05-29