Guides
How to run AI on your own computer
Open-weight models can run on a laptop with free tools such as Ollama or LM Studio. Your text never leaves the machine.
In short
Oossa's checklist: memory decides what you can run; roughly 8 GB of RAM fits small models, 32 GB or more fits mid-sized ones. Quantised versions (Q4, GGUF, MLX) use less memory with some loss of quality. Download models only from the official publisher, and check the licence before commercial use.
Oossa · Published by Oossa:
Models →
Today
Models
Amazon renames Kindle Unlimited to Kindle+ and adds AI audiobooks
Amazon says Kindle+ keeps Kindle Unlimited’s $12 monthly price and borrowing model, while adding more audiobooks, including titles narrated by AI.
Models
Gartner Survey Finds Few Companies See Major AI Returns
Only 13% of surveyed technology leaders reported major or transformative returns from AI, while many expect higher operating costs.
Models
Uber expands ChatGPT Work to all 30,000 employees
Uber says its global workforce will use ChatGPT Work after an earlier 1,000-person pilot. The company has not disclosed the rollout’s cost.
Models
Google DeepMind releases detailed global forest type map
The new Forest Typology 2020 map shows every 10‑meter patch of land as natural, planted or farmed forest, with yearly changes from 2017‑2025.
Models
llama.cpp release adds GQA support and new tokenizer features
The open‑source llama.cpp library now handles non‑standard GQA models and a BPE tokenizer, with expanded platform builds.
Models
AI21 says harness changes cut GitLab review costs 97.7%
AI21 tested GitLab Duo Code Review on 50 public pull requests. DeepSeek V4 Flash and compacted prompts cut measured cost while keeping benchmark F1 near baseline.
