--- title: "#local-inference articles | Hashnode" description: "Explore 6 articles tagged #local-inference on Hashnode. Tutorials, guides, and how-tos from the community." url: "https://hashnode.com/tag/local-inference" --- Tag # #local-inference 6 posts · 0 followers [Praise James](https://hashnode.com/@thepraisejames) · [Oct 25](https://hashnode.com/posts/build-a-local-ai-agent-on-a-raspberry-pi-5-with-vectorai-db/6ade3243e47b2d570eb64d1c) ### [Build a local AI agent on a Raspberry Pi 5 with VectorAI DB](https://actiandev.hashnode.dev/build-a-local-ai-agent-on-a-raspberry-pi-5-with-vectorai-db?utm_source=hashnode&utm_medium=feed) Local inference, semantic memory, and persistent storage in 2.38 GiB of RAM on a single board. 15 min read · [actiandev.hashnode.dev](https://actiandev.hashnode.dev/build-a-local-ai-agent-on-a-raspberry-pi-5-with-vectorai-db?utm_source=hashnode&utm_medium=feed) [Ikraj Singh](https://hashnode.com/@ikraj-singh) · [Sep 29](https://hashnode.com/posts/local-llm-inference-what-to-know-before-you-start/6abb362687ee11aa2e1512ed) ### [Local LLM Inference: What to Know Before You Start](https://ikrajsingh.hashnode.dev/local-llm-inference-what-to-know-before-you-start?utm_source=hashnode&utm_medium=feed) My experience navigating models, servers, runtimes, and hardware compatibility. 10 min read · [ikrajsingh.hashnode.dev](https://ikrajsingh.hashnode.dev/local-llm-inference-what-to-know-before-you-start?utm_source=hashnode&utm_medium=feed) [7](https://hashnode.com/posts/local-llm-inference-what-to-know-before-you-start/6abb362687ee11aa2e1512ed) [Learn with HJ](https://hashnode.com/@hardeepjethwani) · [Jul 11](https://hashnode.com/posts/ai-pcs-and-neural-chips-what-npus-actually-do/6a5262ae6aa432b551ce6f85) ### [AI PCs and Neural Chips: What NPUs Actually Do](https://hardeepjethwani.hashnode.dev/ai-pcs-and-neural-chips-what-npus-actually-do?utm_source=hashnode&utm_medium=feed) Explain NPUs, GPUs, CPUs, local inference, battery life, and practical user benefits. 6 min read · [hardeepjethwani.hashnode.dev](https://hardeepjethwani.hashnode.dev/ai-pcs-and-neural-chips-what-npus-actually-do?utm_source=hashnode&utm_medium=feed) [Marc Wojcik](https://hashnode.com/@thecgaigroup) · [Jun 6](https://hashnode.com/posts/gemma-4-local-inference-agents/6a248fe5893102599e491b48) ### [A 12B You Can Run on a Laptop: Local Inference Grows Up](https://blog.thecgaigroup.com/gemma-4-local-inference-agents?utm_source=hashnode&utm_medium=feed) A model small enough for a laptop just changed the local-vs-cloud math for agents 16 min read · [blog.thecgaigroup.com](https://blog.thecgaigroup.com/gemma-4-local-inference-agents?utm_source=hashnode&utm_medium=feed) [Jangwook Kim](https://hashnode.com/@effloow) · [May 9](https://hashnode.com/posts/gemma-4-mtp-multi-token-prediction-inference-guide-2026/69ff25f3aa311c28e328ce89) ### [Gemma 4 MTP Drafters: How Multi-Token Prediction Delivers 2x+ Faster Local Inference](https://effloow.hashnode.dev/gemma-4-mtp-multi-token-prediction-inference-guide-2026?utm_source=hashnode&utm_medium=feed) On May 5, 2026, Google released Multi-Token Prediction (MTP) drafters for the Gemma 4 family. The headline claim — up to 3x inference speedup — is technically accurate on specific hardware. The more realistic number for most developer setups is 1.7x ... 6 min read · [effloow.hashnode.dev](https://effloow.hashnode.dev/gemma-4-mtp-multi-token-prediction-inference-guide-2026?utm_source=hashnode&utm_medium=feed) [Vlad Butacu](https://hashnode.com/@vlad-omniforge) · [Apr 15](https://hashnode.com/posts/your-local-llm-is-slow-because-of-five-config-flags/69e00519f95c47e87f56f05b) ### [Your Local LLM Is Slow Because of Five Config Flags](https://omniforge.online/blog/your-local-llm-is-slow-because-of-five-config-flags?utm_source=hashnode&utm_medium=feed) KV cache, context size, and batch size control more of the performance budget than most people realize 8 min read · [omniforge.online](https://omniforge.online/blog/your-local-llm-is-slow-because-of-five-config-flags?utm_source=hashnode&utm_medium=feed) [Alan West](https://hashnode.com/@alanwest) · [Apr 6](https://hashnode.com/posts/ollama-just-got-93-faster-on-mac-heres-how-to-enable-it/69d3750fee506cf539ce787d) ### [Ollama Just Got 93% Faster on Mac. Here's How to Enable It.](https://alan-west.hashnode.dev/ollama-just-got-93-faster-on-mac-heres-how-to-enable-it?utm_source=hashnode&utm_medium=feed) Ollama 0.19 ships with an MLX backend preview that nearly doubles decode speed on Apple Silicon. Step-by-step guide to enabling it, benchmarking before and after, hardware requirements, and an honest look at what works and what doesn't yet. 5 min read · [alan-west.hashnode.dev](https://alan-west.hashnode.dev/ollama-just-got-93-faster-on-mac-heres-how-to-enable-it?utm_source=hashnode&utm_medium=feed) [Up2itnow Bill Wilson](https://hashnode.com/@up2itnow) · [Mar 22](https://hashnode.com/posts/the-sovereign-payment-agent-running-agentpay-mcp-locally-with-flash-moe/69c0261a8f353b17db789c23) ### [The Sovereign Payment Agent: Running AgentPay MCP Locally with Flash-MoE](https://ai-agent-economy.hashnode.dev/the-sovereign-payment-agent-running-agentpay-mcp-locally-with-flash-moe?utm_source=hashnode&utm_medium=feed) A 397B MoE model with tool calling on a MacBook + non-custodial payments = the first documented sovereign payment agent architecture 5 min read · [ai-agent-economy.hashnode.dev](https://ai-agent-economy.hashnode.dev/the-sovereign-payment-agent-running-agentpay-mcp-locally-with-flash-moe?utm_source=hashnode&utm_medium=feed)