DEV Community

#ollama

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
How Much GPU You Actually Need for Local Code Review in 2026

How Much GPU You Actually Need for Local Code Review in 2026

Comments
5 min read
Ollama 0.32.0の「ローカルAIエージェント」を本番機で試せなかった話 — 共有GPUインフラのバージョンを上げない判断と、リリースノートと現物のドリフト

Ollama 0.32.0の「ローカルAIエージェント」を本番機で試せなかった話 — 共有GPUインフラのバージョンを上げない判断と、リリースノートと現物のドリフト

Comments
1 min read
Run AI Models Locally with Ollama: Full Privacy, Zero Cost

Run AI Models Locally with Ollama: Full Privacy, Zero Cost

Comments
2 min read
I Gave My AI a Memory. It Changed Everything.

I Gave My AI a Memory. It Changed Everything.

Comments
5 min read
My Local AI Stack, Mid-2026: What Survived and What I Dropped

My Local AI Stack, Mid-2026: What Survived and What I Dropped

2
Comments
5 min read
Six queries, three runs, every mean 8 — and the fine-tune wasn't why

Six queries, three runs, every mean 8 — and the fine-tune wasn't why

Comments
6 min read
Local LLMs for an Infra-Monitoring Agent: The Ollama think Bug, and Why I Still Chose a Cloud Model

Local LLMs for an Infra-Monitoring Agent: The Ollama think Bug, and Why I Still Chose a Cloud Model

Comments 2
6 min read
I Built a Personal AI That Actually Knows My Projects (RAG + Ollama, Zero Cloud)

I Built a Personal AI That Actually Knows My Projects (RAG + Ollama, Zero Cloud)

Comments
5 min read
AI ERD Design With Ollama: Schema Help That Never Leaves Your Machine

AI ERD Design With Ollama: Schema Help That Never Leaves Your Machine

Comments
5 min read
Run Qwen Coder & DeepSeek Locally: The 2026 Free AI Pair-Programmer Setup

Run Qwen Coder & DeepSeek Locally: The 2026 Free AI Pair-Programmer Setup

Comments
7 min read
Ollama Model Loading RCE: Three Years of the Same Bug Class, One Self-Hosted LLM Runtime

Ollama Model Loading RCE: Three Years of the Same Bug Class, One Self-Hosted LLM Runtime

Comments
7 min read
It Fits and It Benchmarks Well. Will It Do Your Job?

It Fits and It Benchmarks Well. Will It Do Your Job?

2
Comments 1
4 min read
One MCP Server, Two Models: An Always-On Ops Agent That Costs $0

One MCP Server, Two Models: An Always-On Ops Agent That Costs $0

Comments
15 min read
I Built a Dead-Simple API Gateway for My Local LLMs in 50 Lines of Python

I Built a Dead-Simple API Gateway for My Local LLMs in 50 Lines of Python

Comments
4 min read
I built a 100% local invoice reader with Ollama + n8n — the real trick was teaching it NOT to guess

I built a 100% local invoice reader with Ollama + n8n — the real trick was teaching it NOT to guess

Comments
2 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.