From d8391ebf99b0d93c7bcc9a5c7b96a0c4b6effd1d Mon Sep 17 00:00:00 2001 From: Sam Rolfe Date: Sat, 6 Jun 2026 16:20:24 +1000 Subject: [PATCH] sam-4screen-desktop 2026-6-6:16:20:24 --- .obsidian/workspace.json | 12 ++++++------ 300 areas/350 AI/LLM - models to consider.md | 12 ++++++++++++ 2 files changed, 18 insertions(+), 6 deletions(-) diff --git a/.obsidian/workspace.json b/.obsidian/workspace.json index 3c8280f..cc87669 100644 --- a/.obsidian/workspace.json +++ b/.obsidian/workspace.json @@ -13,12 +13,12 @@ "state": { "type": "markdown", "state": { - "file": "300 areas/350 AI/Pi Agent Extensions & Skills.md", - "mode": "source", + "file": "300 areas/350 AI/LLM - models to consider.md", + "mode": "preview", "source": true }, "icon": "lucide-file", - "title": "Pi Agent Extensions & Skills" + "title": "LLM - models to consider" } } ] @@ -181,10 +181,10 @@ "state": { "type": "file-properties", "state": { - "file": "300 areas/350 AI/Pi Agent Extensions & Skills.md" + "file": "300 areas/350 AI/LLM - models to consider.md" }, "icon": "lucide-info", - "title": "File properties for Pi Agent Extensions & Skills" + "title": "File properties for LLM - models to consider" } } ], @@ -209,8 +209,8 @@ }, "active": "b145af38583e5d9a", "lastOpenFiles": [ - "300 areas/350 AI/Security NPM packages tools.md", "300 areas/350 AI/Pi Agent Extensions & Skills.md", + "300 areas/350 AI/Security NPM packages tools.md", "300 areas/350 AI/Automated Agentic Tools.md", "300 areas/350 AI/AI Tools to try.md", "400 resources/410 Web Pages/Website Design AI.md", diff --git a/300 areas/350 AI/LLM - models to consider.md b/300 areas/350 AI/LLM - models to consider.md index c4f920f..b2f6749 100644 --- a/300 areas/350 AI/LLM - models to consider.md +++ b/300 areas/350 AI/LLM - models to consider.md @@ -22,3 +22,15 @@ This is a multi-layer tool that as split into planner, coordinator and worker ag | **Kimi K2.6** | High tolerance for parallel tasks & long chains | Open-Weight / API | Multi-agent collaboration frameworks | | **GLM 4.5 Air** | Toggleable Native "Thinking Mode" for reasoning | OpenRouter (Free) | Hybrid text and complex API automation | | **NVIDIA Nemotron 3 Nano (30B A3B)** | Local, secure agents that do not rely on cloud APIs | Open-Weight | Local, secure desktop agent loops | + +### Free models + + +| Model | Best For | Key Strength | +| :--- | :--- | :--- | +| **Owl-Alpha** | General Purpose | Balanced performance, great free baseline | +| **Llama 3.3 70B** | General Purpose | Premium intelligence, handles complex reasoning | +| **Gemma 4 31B** | Everyday Tasks | Fast response times, great for summarizing | +| **DeepSeek V4 Flash**| Logic & Math | Rapid-fire problem solving, structured data | +| **Qwen 3 Coder** | Coding & Tech | Writing scripts, debugging, Excel formulas | +| **NVIDIA Nemotron** | Long Documents | Massive context window for deep research |