AI on Mac

Search

What are you looking for?

Search all articles about local LLMs, tools and Apple Silicon.

Popular searches

#llama.cpp 4 articles

Recent Latest articles

Model News

Qwen3.8-Flash Explained: Pricing, 1M Context, Benchmarks, and Flash-Next

A source-checked guide to Qwen3.8-Flash pricing, its 1M context window, API features, benchmarks, and the separate Flash-Next open-weight release.

· 10 min read
Model News

Tencent Hy4 Preview: 770B MoE, 1M Context, Pricing and Benchmarks

Tencent Hy4 preview checked: 770B/49B MoE, 1M context, API limits, pricing, Apache 2.0, self-hosting hardware and the evidence behind its benchmarks.

· 10 min read
Model News

DeepSeek V4 Pro 0813: Pricing, Benchmarks and the Mac Reality Check

DeepSeek V4 Pro 0813: API pricing, agent benchmarks, Pro vs Flash, API caveats and why the 1.6T model is not a realistic local Mac model.

· 12 min read

Browse Tags by topic

#apple-silicon 38 #mac 29 #ollama 20 #cloud-ai 18 #api 17 #agents 16 #coding 15 #local-ai 14 #mlx 12 #open-weights 10 #llm 9 #vision 9 #moe 8 #qwen 8 #pricing 6 #benchmarks 6 #benchmark 6 #google 6 #local-models 6 #multimodal 5 #openrouter 5 #reasoning 5 #privacy 5 #lm-studio 5

Choose which optional services may load. Required functions stay active so language, theme and consent choices work.

Required functions

Stores language, theme and your consent selection locally in the browser. These functions are required for the website.

Always on
Google Analytics 4

Measures page views and usage patterns so content and navigation can be improved. Loaded only after consent.

Disabled
Advertising & ads

Allows advertising features. Personalized ads in the EEA, UK and Switzerland require a suitable Google-certified CMP.

Disabled

You can change your selection in the footer at any time. Details about hosting, analytics, advertising, third parties and your rights are in the Privacy Policy.

Privacy Policy