From Dev.to Community
Tech Articles
Curated developer articles, tutorials, and guides — auto-updated hourly
Rickesh T NAug 24, 2026 • 3 min read
My inference server decided my second GPU no longer exists. Here is how I got it back without upgrading a driver.
My desktop runs two mismatched GPUs: a 20GB Ampere card and a 16GB Pascal Tesla. For months, a 21GB....
#gpu#llamacpp#ollama#homelab
0 0
Syed Anzar4d ago • 7 min read
Your LLM Returns JSON That Isn't JSON: A Robust Structured-Output Pipeline for Local Models
Stop trusting your local LLM's JSON. Combine Ollama schema-constrained decoding with a resilient par...
#llm#python#ollama#json
2 0
Sam Hartley4d ago • 6 min read
I Replaced All My Cloud AI With Local Models — Here's What Actually Broke
I Replaced All My Cloud AI With Local Models — Here's What Actually Broke I write a lot...
#ai#llm#selfhosted#ollama
0 0
Nathan C.3d ago • 4 min read
Flash Onyx 2.2: teaching a local model law and game feel
Starting work on the next Flash Onyx. Two new domains in the system prompt, and why I cut both of th...
#ai#ollama#localllm#opensource
1 0
Umair BilalAug 23, 2026 • 8 min read
Fix Local LLM Quality: Context Stacking & Rope Freq Tweaks
Your local LLMs feel dumb? I fixed local LLM quality by combining a context-stacking prompt techniqu...
#localllms#aiagents#ollama#llamacpp
0 0
Nathan C.5d ago • 6 min read
Flash Onyx 2.1, one day later: my model spent 400 tokens thinking and returned an empty string
I posted Onyx 2 yesterday. Then I found out why it felt so slow, and the answer was sitting in the s...
#ai#llm#ollama#opensource
0 1
Nerav DoshiAug 24, 2026 • 2 min read
Queried the Local Embeddings Store for the First Time
Context: Building the vector store in the last entry was only half the job — the actual point of...
#ollama#rag#embeddings#chromadb
0 0
Nerav Doshi4d ago • 4 min read
Chunked a Document and Found a New Retrieval Problem
Context: Chunking means splitting a long document into smaller overlapping pieces before embedding.....
#ollama#rag#embeddings#chromadb
0 0
ghostAug 21, 2026 • 0 min read
Integrating Ollama into a native desktop app: field notes
A post by ghost
#ollama#ai#desktop#api
0 0
Nokka5d ago • 1 min read
Ollama v0.33 เปิดตัว, ใช้ Claude Desktop กับโมเดล local ได้ด้วย toggle เดียว
Ollama v0.33 เปิดตัว, ใช้ Claude Desktop กับโมเดล local ได้ด้วย toggle เดียว โดย Nokka...
#ollama#ai#claude#opensource
0 0
Amrendra N Mishra3d ago • 1 min read
5 Local AI Tools That Replace Expensive Cloud APIs
The Problem With Cloud AI Every token costs money. Every API call adds up. And your data...
#ai#ollama#productivity#tutorial
0 0
Patrick HughesAug 22, 2026 • 4 min read
My local LLM eval hid four token caps
My 5090-rig eval uses four output caps: 50, 180, 192, and 256 tokens. A score without the cap is not...
#localllm#ollama#rtx5090#5090reports
0 0
Patrick HughesAug 24, 2026 • 4 min read
Why a Failed Local LLM Benchmark Row Still Matters
A failed local LLM row marks the test boundary. My RTX 5090 report shows why quality, speed, and set...
#localllm#modelevaluation#ollama#rtx5090
0 0
Laptop Hưng Phát4d ago • 3 min read
Local RAG đọc tài liệu nhanh nhưng RAM 16GB có đủ chạy không
Lập trình viên và kỹ sư phần mềm thường xuyên phải đối soát tài liệu kỹ thuật, API nội bộ hoặc mã...
#ollama#webdev#typescript#performance
0 0
Patrick Hughes6d ago • 5 min read
How to Calculate Local LLM Energy per Token
My RTX 5090 test shows how watts and output rate become joules per token, and why the faster of two ...
#localllm#modelevaluation#ollama#rtx5090
0 0
Laptop Hưng PhátAug 24, 2026 • 3 min read
Đo RAM và SSD khi dev chạy Docker kèm Ollama trên laptop
Nhiều lập trình viên thường tập trung vào xung nhịp vi xử lý mà bỏ quên bài toán tắc nghẽn bộ nhớ kh...
#ollama#ram#benchmark#docker
0 0
Patrick Hughes5d ago • 5 min read
49W Average Hid a 338W Burst on Gemma 26B
Gemma 4 26B Q4_K_M averaged 49 W on a long RTX 5090 run and peaked at 338 W. Keep both watt numbers ...
#localllm#gguf#ollama#rtx5090
0 0
Nokka6d ago • 2 min read
ตั้งค่า Opencodex + Ollama, ใช้ Claude Code กับโมเดล local
ตั้งค่า Opencodex + Ollama บน MacBook, ใช้ Claude Code และ Codex กับโมเดล local ฟรี โดย...
#ai#opensource#ollama#claude
0 0
Nexus Intelligence Research3d ago • 5 min read
How to Run 15 AI Agents on a $5/Month VPS (Complete Guide)
Production setup: Ollama + free APIs + screen sessions + daemon monitoring
#ai#agents#vps#ollama
0 0