Juanchi.dev
Digital Native · real systems
·
HomeCVBlogLabContact
Skip to content
Juanchi.dev
Digital Native · real systems
·
HomeCVBlogLabContact
AllExperimentsTutorialsOpinionReflectionsTechnologyHistory

Tag: ollama

7
Sep 03 2026

DeepSeek Reasonix: A Technical Read on a Native Coding Agent with Aggressive Caching

DeepSeek Reasonix shows up as a native coding agent with aggressive caching and low cost. Before you adopt it or dismiss it, there's a more useful question: what specific problem does it actually solve in a real stack, and what reproducible experiment confirms that?

Sep 03 2026 · 9′ · Opinion · LLM · ia

9′
Aug 02 2026

Qwen3 locally with Ollama: what changed in the architecture and whether it's worth switching

Qwen3 landed with thinking mode and real improvements in code generation. But before you replace the model already running in your Ollama setup, there are technical questions you need to answer first. I answer them here without selling hype.

Aug 02 2026 · 9′ · Tutorials · TypeScript · Inferencia Local

9′
Jun 16 2026

My Homelab AI Dev Platform: What Problem It Actually Signals and Where the Limits Are

The homelabber community is building local AI dev platforms and the discussion is genuinely interesting. I have some observations that go beyond the initial excitement — and a checklist so you can decide whether the experiment is actually worth it.

Jun 16 2026 · 9′ · Opinion · TypeScript · LLM

9′
Jun 15 2026

Rio de Janeiro's "Own LLM" Looks Like a Merge: What to Read Between the Lines

A municipality announces its "own" LLM and the technical community discovers it might be a merge of an existing model. My read: the real problem isn't the fraud — it's that almost nobody knows how to verify it. Here's the checklist.

Jun 15 2026 · 9′ · Opinion · LLM · open source

9′
May 17 2026

Show HN: Needle distilled Gemini tool calling into 26M parameters — technical read, zero hype

A 26M parameter model trained via Gemini distillation for tool calling showed up on HN and made me stop everything. Not to celebrate — to understand what real problem it points at, where the limits actually are, and whether it belongs in a stack like mine.

May 17 2026 · 8′ · Opinion · TypeScript · LLM

8′
Apr 16 2026

The Local LLM Ecosystem Doesn't Need Ollama (And That Made Me Uncomfortable)

I've been team Ollama since day one. Last week I tried replacing it with raw llama.cpp and a minimal wrapper. What I found forced me to rethink something I thought I'd already figured out: Ollama solves UX, not infrastructure.

Apr 16 2026 · 6′ · Opinion · docker · LLM

6′
Apr 13 2026

Apple as the AI 'Loser' That Ends Up Winning: I Lived It When Anthropic Ghosted Me for a Month

Apple's 'accidental moat': privacy wasn't a feature — it was the Plan B nobody took seriously. I have an M3 Pro and the local inference numbers are no longer a joke. Real benchmarks inside.

Apr 13 2026 · 9′ · Reflections · ia · modelos locales

9′

Series

  • Open Data and Creativity2
  • Awesome Curated: The Tools10
  • Awesome Curated1
See all

Clusters

  • Software architecture

Categories

  • Experiments98
  • Tutorials85
  • Opinion44
  • Reflections18
  • Technology8
  • History6

Tags

  • #TypeScript
  • #arquitectura
  • #nextjs
  • #railway
  • #java
  • #LLM
  • #postgresql
  • #ia
  • #prisma
  • #software-architecture
  • #firma-digital
  • #AI

Popular

  1. 01pnpm vs npm vs yarn vs bun: The Real Comparison Nobody Gives You in 2025
  2. 02Next.js App Router: The Guide I Wish I Had When I Migrated from Pages Router
  3. 03TypeScript: The Patterns I Actually Use Every Single Day
  4. 04Docker for Node.js Developers: From Zero to Production Without Losing Your Mind
  5. 05Your Digital Signing Cryptography Has an Expiration Date: What NIST Published and How to Migrate Your HSM

Newsletter

One email a week. What I'm learning, building, and breaking.

Series

  • Open Data and Creativity2
  • Awesome Curated: The Tools10
  • Awesome Curated1
See all

Clusters

  • Software architecture

Categories

  • Experiments98
  • Tutorials85
  • Opinion44
  • Reflections18
  • Technology8
  • History6

Tags

  • #TypeScript
  • #arquitectura
  • #nextjs
  • #railway
  • #java
  • #LLM
  • #postgresql
  • #ia
  • #prisma
  • #software-architecture
  • #firma-digital
  • #AI

Popular

  1. 01pnpm vs npm vs yarn vs bun: The Real Comparison Nobody Gives You in 2025
  2. 02Next.js App Router: The Guide I Wish I Had When I Migrated from Pages Router
  3. 03TypeScript: The Patterns I Actually Use Every Single Day
  4. 04Docker for Node.js Developers: From Zero to Production Without Losing Your Mind
  5. 05Your Digital Signing Cryptography Has an Expiration Date: What NIST Published and How to Migrate Your HSM

Newsletter

One email a week. What I'm learning, building, and breaking.

Juanchi.dev is Juan Torchia’s public notebook — architecture, real systems and product decisions. Written and reviewed by hand in Buenos Aires. Built with Next.js, Prisma and PostgreSQL; deployed on Railway. No third-party trackers beyond aggregate analytics.

GitHubRSS© 2026 Juan Torchia · All rights reserved.

Real code. Unfiltered takes.

Architecture, real systems, product decisions and technical lessons. Everything reviewed with my own judgment before it ships.

222 articles published

Blog
Uses
Now