Ollama

Tool for easily running and managing open large language models (LLMs) such as Llama and Gemma on your own machine.

Latest articles and summaries (4)

PC Watchby 宇都宮 充11/12/2026
AI summary

Unsloth released a quantized version of the 27B parameter Qwen3.8-27B model, enabling it to run on 12GB of memory.

  • •The model was released using a new quantization technique called Dynamic v3.1.
  • •It is distributed for free in GGUF format under the Apache License 2.0 on Hugging Face.
  • •The model can be run on environments such as the Unsloth Desktop app, llama.cpp, and Ollama.
#LLM / Model Trends#Semiconductors & Infrastructure#Generative AI Tools & Use
Hacker NewsHN submitter: soloyo11/6/2026
AI summary

A 100% offline survival assistant for Windows, Linux, and macOS that utilizes local AI via llama.cpp or Ollama and integrates Kiwix libraries.

  • •Provides guides on water, fire, food, first aid, and alcohol in Portuguese, English, and Spanish.
  • •Runs local AI using tools such as llama.cpp and Ollama.
  • •Integrates Kiwix libraries to enable offline information access.
#Generative AI Tools & Use#LLM / Model Trends
Hacker NewsHN submitter: 0o_MrPatrick_o09/14/2026
AI summary

AnthropicのOpusから自己ホスティング環境のOllamaへ大規模なプリプロンプトを移行する際の技術的な落とし穴や注意点について解説している。

  • •35kbという大規模なプリプロンプトをモデル間移動させる際の技術的課題を詳述
  • •OpusとOllama(LLM)間の挙動の違いや、コンテキスト処理の相違点を指摘
  • •自己ホスティング環境でのプロンプト最適化とトラブルシューティングの手法を紹介
#LLM / Model Trends#Generative AI Tools & Use