AI is going insane now… imagine creating this with models like; Grok 4.6 and Gemini 3.7
GTP-5.6 and Opus 5 will be costly, Kimi K3, DeepSeek V4, and Qwen 3.8 will be cheap but low quality.
AI grifters would have you believe Apple Silicon is suitable for agentic tasks.
Here's M3 Ultra (512GB) running DwarfStar DeepSeek V4 Flash, taking 1 minute to respond to "hi" on an empty chat. MLX performance is even worse than this. But sure, Apple is great for local AI 😆
Hermes Studio perfects FPS using DeepSeek-V4-Flash!
Can Qwen3.8-27B and Bionic surpass this? ⚔️
Agent OS model guide: which AI to use for what job.
Plus one weird trick from the creator of Claude Code. The stack that works right now: → Orchestrator: Claude Fable 5. The best brain to run the whole system. → Agent work: DeepSeek V4 Pro. Very agentic. Very affordable.
You have reached the end of the archive
All of deepseek