Local AI Tutorials, Tools, and Guides

New11 min read

EmbeddingGemma 2 Guide: Local Multimodal Embeddings for Code

EmbeddingGemma 2 is a 740M open model that embeds code, images, video and audio in one space. Specs, Matryoshka storage math, and where it breaks.

Google Gemma Embeddings

10 min read

Hermes Agent Guide (2026): What It Is, Local Setup With Ollama, Skills, and Hermes vs OpenClaw

Hermes Agent is Nous Research's open-source, self-improving AI agent. Run it locally with Ollama, see how its skills system works, and compare it with OpenClaw.

Hermes Agent Nous Research Ollama

7 min read

GitHub Copilot for JetBrains Gains Persistent Memory and Ollama BYOK

GitHub Copilot for JetBrains adds memory across chat sessions, Ollama as a BYOK provider, and enterprise settings for MCP access. What each feature does.

News GitHub Copilot AI Coding

7 min read

Cactus Needle 2: The 14MB Agentic LLM That Runs on a Raspberry Pi 5

Cactus open-sourced Needle 2, a 45M-parameter agentic LLM in a single 14MB binary that runs a full tool-calling session in 28MB of RAM. 500 tok/s on a Raspberry Pi 5, ESP32-S3 class parts, Apache 2.0. Here is what the benchmarks actually show.

ai-models open-source local-ai

8 min read

Muse Glimmer 30B: Meta's Open-Weight Local Agent Model, Benchmarks, and Hardware Reality

Muse Glimmer 30B is Meta's Apache 2.0 open-weight multimodal agent model that runs in 24GB. Benchmarks, hardware reality and what the numbers actually say.

ai-models open-source ai-agents

6 min read

Running Gemma 4 26B at 5 Tokens/Sec on a 13-Year-Old Xeon With No GPU

Gemma 4 26B on a 2013 Xeon with no GPU: how a sub-$300 box reached about 5 tokens/sec, the silent MoE bug behind the gibberish, and the upstream fix.

News Hacker News LLM

6 min read

Colibri: Run GLM 5.2 on a 32GB Laptop With Disk Streaming

A solo developer built a 1,300-line C inference engine that runs the 744B GLM 5.2 model on consumer hardware by streaming routed experts from disk.

News Hacker News LLMs

6 min read

Kokoro: Local, CPU-Friendly TTS That Actually Sounds Good

An 82M parameter text-to-speech model that runs on CPU and produces high-quality speech across multiple languages - no cloud APIs or GPU required.

News Hacker News AI

7 min read

Program-as-Weights Turns Prompts Into Local Fuzzy Functions

Program-as-Weights compiles prompts into compact local adapters that act as fuzzy functions. What the paper claims and where developers could use it first.

AI Coding Local AI LLM

7 min read

GLM-5.2 Local Deployment: Running Z.ai's 744B Model on Consumer Hardware

Run GLM-5.2 locally with Unsloth dynamic quantization: hardware math for a 256GB Mac or 24GB GPU, quantization tradeoffs and lessons from the HN thread.

News Hacker News LLMs

8 min read

DiffusionGemma: Google Bets Diffusion Can Make Text Generation 4x Faster

DiffusionGemma is Google's 26B MoE open model that generates 256-token blocks in parallel. What diffusion generation means for latency and local inference.

ai open-source inference

9 min read

What Is Cline? The Open-Source AI Coding Agent for VS Code

Cline is a free, open-source VS Code extension for agentic AI coding. Bring your own model, a cloud API or a local one via Ollama, with no vendor lock-in.

AI Coding VS Code Open Source

New11 min read

EmbeddingGemma 2 Guide: Local Multimodal Embeddings for Code

EmbeddingGemma 2 is a 740M open model that embeds code, images, video and audio in one space. Specs, Matryoshka storage math, and where it breaks.

Google Gemma Embeddings

10 min read

Hermes Agent Guide (2026): What It Is, Local Setup With Ollama, Skills, and Hermes vs OpenClaw

Hermes Agent is Nous Research's open-source, self-improving AI agent. Run it locally with Ollama, see how its skills system works, and compare it with OpenClaw.

Hermes Agent Nous Research Ollama

7 min read

GitHub Copilot for JetBrains Gains Persistent Memory and Ollama BYOK

GitHub Copilot for JetBrains adds memory across chat sessions, Ollama as a BYOK provider, and enterprise settings for MCP access. What each feature does.

News GitHub Copilot AI Coding

7 min read

Cactus Needle 2: The 14MB Agentic LLM That Runs on a Raspberry Pi 5

ai-models open-source local-ai

8 min read

Muse Glimmer 30B: Meta's Open-Weight Local Agent Model, Benchmarks, and Hardware Reality

Muse Glimmer 30B is Meta's Apache 2.0 open-weight multimodal agent model that runs in 24GB. Benchmarks, hardware reality and what the numbers actually say.

ai-models open-source ai-agents

6 min read

Running Gemma 4 26B at 5 Tokens/Sec on a 13-Year-Old Xeon With No GPU

Gemma 4 26B on a 2013 Xeon with no GPU: how a sub-$300 box reached about 5 tokens/sec, the silent MoE bug behind the gibberish, and the upstream fix.

News Hacker News LLM

6 min read

Colibri: Run GLM 5.2 on a 32GB Laptop With Disk Streaming

A solo developer built a 1,300-line C inference engine that runs the 744B GLM 5.2 model on consumer hardware by streaming routed experts from disk.

News Hacker News LLMs

6 min read

Kokoro: Local, CPU-Friendly TTS That Actually Sounds Good

An 82M parameter text-to-speech model that runs on CPU and produces high-quality speech across multiple languages - no cloud APIs or GPU required.

News Hacker News AI

7 min read

Program-as-Weights Turns Prompts Into Local Fuzzy Functions

Program-as-Weights compiles prompts into compact local adapters that act as fuzzy functions. What the paper claims and where developers could use it first.

AI Coding Local AI LLM

7 min read

GLM-5.2 Local Deployment: Running Z.ai's 744B Model on Consumer Hardware

Run GLM-5.2 locally with Unsloth dynamic quantization: hardware math for a 256GB Mac or 24GB GPU, quantization tradeoffs and lessons from the HN thread.

News Hacker News LLMs

8 min read

DiffusionGemma: Google Bets Diffusion Can Make Text Generation 4x Faster

DiffusionGemma is Google's 26B MoE open model that generates 256-token blocks in parallel. What diffusion generation means for latency and local inference.

ai open-source inference

9 min read

What Is Cline? The Open-Source AI Coding Agent for VS Code

Cline is a free, open-source VS Code extension for agentic AI coding. Bring your own model, a cloud API or a local one via Ollama, with no vendor lock-in.

AI Coding VS Code Open Source

LOCAL AI

Muse Spark Open Weights: 816B Model, Benchmarks, and How to Run It

EmbeddingGemma 2 Guide: Local Multimodal Embeddings for Code

Hermes Agent Guide (2026): What It Is, Local Setup With Ollama, Skills, and Hermes vs OpenClaw

GitHub Copilot for JetBrains Gains Persistent Memory and Ollama BYOK

Cactus Needle 2: The 14MB Agentic LLM That Runs on a Raspberry Pi 5

Muse Glimmer 30B: Meta's Open-Weight Local Agent Model, Benchmarks, and Hardware Reality

Running Gemma 4 26B at 5 Tokens/Sec on a 13-Year-Old Xeon With No GPU

Colibri: Run GLM 5.2 on a 32GB Laptop With Disk Streaming

Kokoro: Local, CPU-Friendly TTS That Actually Sounds Good

Program-as-Weights Turns Prompts Into Local Fuzzy Functions

GLM-5.2 Local Deployment: Running Z.ai's 744B Model on Consumer Hardware

DiffusionGemma: Google Bets Diffusion Can Make Text Generation 4x Faster

What Is Cline? The Open-Source AI Coding Agent for VS Code

Keep exploring Local AI

LOCAL AI

Muse Spark Open Weights: 816B Model, Benchmarks, and How to Run It

EmbeddingGemma 2 Guide: Local Multimodal Embeddings for Code

Hermes Agent Guide (2026): What It Is, Local Setup With Ollama, Skills, and Hermes vs OpenClaw

GitHub Copilot for JetBrains Gains Persistent Memory and Ollama BYOK

Cactus Needle 2: The 14MB Agentic LLM That Runs on a Raspberry Pi 5

Muse Glimmer 30B: Meta's Open-Weight Local Agent Model, Benchmarks, and Hardware Reality

Running Gemma 4 26B at 5 Tokens/Sec on a 13-Year-Old Xeon With No GPU

Colibri: Run GLM 5.2 on a 32GB Laptop With Disk Streaming

Kokoro: Local, CPU-Friendly TTS That Actually Sounds Good

Program-as-Weights Turns Prompts Into Local Fuzzy Functions

GLM-5.2 Local Deployment: Running Z.ai's 744B Model on Consumer Hardware

DiffusionGemma: Google Bets Diffusion Can Make Text Generation 4x Faster

What Is Cline? The Open-Source AI Coding Agent for VS Code

Keep exploring Local AI

LOCAL AI

Muse Spark Open Weights: 816B Model, Benchmarks, and How to Run It

Keep exploring Local AI

Get Smarter About AI Dev

LOCAL AI

Muse Spark Open Weights: 816B Model, Benchmarks, and How to Run It

Keep exploring Local AI

Get Smarter About AI Dev