Tag feed

#local-ai

59 posts0 followers

Explore Hashnode

Alternatives

Trending tags this week

TStarini sunilai-content-utilties.hashnode.dev1d ago · 4 min read

What Your Documents Mean, Not Just What They Say

On this page A Tiny Experiment Why Keywords Fail Meaning Without Matching Words The Hidden Layer A Simple Mental Model Try It Yourself The Aha Moment The Hidden Signal In the previous artic

0

NCNube Colectivanubecolectiva.hashnode.dev1d ago · 5 min read

6 Free Local AI Models That Are Getting Close to Claude in 2026

For years, models like Claude became the reference point for developers, writers, researchers, and professionals who needed strong reasoning, long-context analysis, coding ability, and natural convers

0

JWJiyao Wengwengjiyao.hashnode.devJun 14 · 12 min read

Gemma 4 for Telephony: I Replaced Two AI Models With One in My Voice Phone Agent — Until I Switched to Chinese

Building a phone agent on a multimodal LLM: dropping faster-whisper and letting Gemma 4 hear the caller directly — a response-time and reply-accuracy benchmark across English, French, and Mandarin My

0

YPYaroslav Pristupacode-friendly.hashnode.devJun 8 · 12 min read

Step-by-step guide to running Gemma-4 26B locally on budget GPUs

The local AI revolution just got a serious upgrade. Google's Gemma-4 26B model, combined with Unsloth's Quantization-Aware Training GGUF formats, makes it possible to run a 26-billion parameter model

0

JCJim Chundevalelaccidentalcomplexity.hashnode.devJun 1 · 18 min read

Part 1: Building a Self-Hosted AI Agent Cluster with Raspberry Pi 5 and Hailo AI HAT+ 2

Introduction So there I was, staring at four Raspberry Pi 5s, two Hailo AI HAT+ accelerators, a growing pile of cables, and the uncomfortable realization that I had built a tiny data center to avoid s

0

TStarini sunilai-content-utilties.hashnode.devMay 30 · 5 min read

What Your Documents Whisper When Nobody's Looking

Most people think important information is easy to spot. Look at enough documents and you will find the important topics because they appear again and again. More mentions = more importance. Right? No

0

MMuzasiomuzasio.hashnode.devMay 27 · 3 min read

I Tried Building a Complex Security Tool with a 1.5B Local Model — Here's What Broke

Problem: I had aider running on Lubuntu, three API keys configured, a detailed architecture diagram, and a clear goal — build a modular forensic data analysis pipeline. What I actually got was token w

0

MMMatt Macoskoineedhemp.hashnode.devMay 10 · 6 min read

The Day Local AI Caught the Cloud: ds4, DeepSeek V4 Flash, and What Just Changed for Devs

If you write code for a living and you've been watching the local-AI space, May 9, 2026 is the date to circle. Salvatore Sanfilippo (yes, the guy who wrote Redis) shipped ds4 — a few thousand lines of hand-written C with Metal compute kernels, built ...

0

MMMatt Macoskoineedhemp.hashnode.devMay 10 · 4 min read

I Just Watched One Hacker Catch Up to a Trillion-Dollar Data Center

▶ Watch the companion video — three engines, one prompt, one MacBook Yesterday Salvatore Sanfilippo — the guy who wrote Redis 15 years ago and ran it solo for over a decade — published a few thousand lines of C code and quietly changed what counts a...

0

JKJangwook Kimeffloow.hashnode.devMay 5 · 10 min read

Qwen3-Coder: 27B Dense Model That Beats 397B MoE (2026)

When Alibaba's Qwen team released Qwen3.6-27B on April 22, 2026, it flipped an assumption that had quietly become dogma in the open-source AI space: that more parameters meant better code. A 27-billion parameter dense model — running on hardware you ...

0

#local-ai

Search Hashnode

#local-ai

Explore Hashnode

Trending tags this week

What Your Documents Mean, Not Just What They Say

6 Free Local AI Models That Are Getting Close to Claude in 2026

Gemma 4 for Telephony: I Replaced Two AI Models With One in My Voice Phone Agent — Until I Switched to Chinese

Step-by-step guide to running Gemma-4 26B locally on budget GPUs

Part 1: Building a Self-Hosted AI Agent Cluster with Raspberry Pi 5 and Hailo AI HAT+ 2

What Your Documents Whisper When Nobody's Looking

I Tried Building a Complex Security Tool with a 1.5B Local Model — Here's What Broke

The Day Local AI Caught the Cloud: ds4, DeepSeek V4 Flash, and What Just Changed for Devs

I Just Watched One Hacker Catch Up to a Trillion-Dollar Data Center

Qwen3-Coder: 27B Dense Model That Beats 397B MoE (2026)