Category
AI
Everything we have published on AI, newest first.

Which local LLMs fit in 8, 12, 16, 24 or 32GB of VRAM
At Q4_K_M and 8K context, 8GB comfortably holds Gemma 2 9B (5.8 GB) and 24GB holds Gemma 3 27B (17.5 GB). Full tables for every common VRAM tier, computed the same way our GPU checker computes them.
Ahmad J · Sep 6, 2026 · 8 min read

How to Choose a Laptop for Local AI
Memory decides whether a model runs at all, bandwidth decides how fast, and thermals decide whether that speed lasts. A short buying guide, plus an interactive picker that turns your priority into a recommendation.
Ahmad J · Sep 5, 2026 · 4 min read

Choosing the right model size for your task
Bigger is not automatically better. A decision framework for matching model size to the job, the latency budget, and the hardware you actually have.
Ahmad J · Sep 4, 2026 · 4 min read

AI Agents Are Moving From Demos to Narrow Jobs
The viral agent demos promised software that does everything. What actually ships are agents scoped to one job with tight guardrails, and that narrowing is the point.
Ahmad J · Sep 3, 2026 · 3 min read

Gemini can now skim a video instead of watching every frame
Google replaced fixed-rate video ingest with an agentic loop that fetches only the moments it needs, and reports up to 88 percent fewer tokens. Every headline figure is an upper bound, the gains concentrate on long video, and the cost saving is just the token saving passed through.
Ahmad J · Sep 2, 2026 · 4 min read
More stories
News · aiWorld Labs' Atlas wins six of seven 3D benchmarks, and you cannot run itSep 2, 2026 · 5 min read
News · aiClaude Fable 5.1 costs 25% less, and its per-token price did not moveSep 2, 2026 · 5 min read
News · aiSmall Models Are Quietly Taking Over the Easy WorkSep 2, 2026 · 3 min read
Guide · aiWhich AI subscription should you actually pay for?Sep 2, 2026 · 7 min read
News · aiDeepSeek's first V4 vision model is MIT-licensed, and 307 GBSep 1, 2026 · 5 min read
News · aiA cheap model solved open math problems, once Google put a team around itSep 1, 2026 · 5 min read
Article · aiSmall AI Models Are Quietly Winning in ProductionAug 14, 2026 · 4 min read