Articles for people who
ship the stack
Rewrites on React, Node.js, TypeScript and AI. A translated body is shown when it exists. If it does not, you see the English text and a note that says so.
Tagged: local-ai
Running the Same OpenAI Chat Loop Locally with Ollama
Run the same OpenAI chat loop locally with Ollama: point the OpenAI Python SDK at localhost and keep your code. No API key, no token bill, no data leaving.
4 min readOrnith-1.0-35B: MoE Quality of a Dense 27B on a MacBook
How a 35B mixture-of-experts model with 3B active parameters compares with Qwen3.6, what it needs to run under llama.cpp, and where it shines or lags.
4 min readQwen3.8-27B on One RTX 3090: 262K Context at 65-80 Tokens per Second
A recipe for running a dense 27B model with full context on a single 24 GB GPU: a tuned llama.cpp fork, a 14.5 GB quant, Turbo3 cache and MTP drafting.
8 min readQwen 3.8-27B Review: Benchmarks, Community Verdict and Hardware Reality
Qwen 3.8-27B against Opus 4.6, DeepSeek V4 Flash and GLM 5.2: benchmarks, what the community reports, tokens per second, and the GPUs that run it well.
8 min readLocal AI After Ollama: Choosing Runtimes in 2026
Ollama is a great on-ramp but a weak long-term control plane. Which local LLM runtime fits each stage after it: llama.cpp, LM Studio, vLLM and related tools.
15 min read
About these articles
Request a 24h estimate
Need the same stack in a production operator layer? Send the brief — estimate within 24 hours.