lm-studio

#lm-studio

Running local models on an M4 with 24GB memory

Hacker News Top ↗ · 2026-05-10 Cached

A guide on running local AI models like Qwen 3.5-9B on an M4 MacBook with 24GB RAM using tools like LM Studio, Ollama, and pi, including specific configuration tips for optimal performance.

0 favorites 0 likes

#lm-studio

@CuiMao: Honestly, running Claude Code locally with LM Studio is surprisingly solid—RTX 5090 handles 64k context at 200+ tokens/s.

X AI KOLs Timeline ↗ · 2026-04-20 Cached

User reports a satisfying experience running Claude Code locally via LM Studio on an RTX 5090, achieving 64k context length and 200+ tokens per second.

0 favorites 0 likes

lm-studio

Running local models on an M4 with 24GB memory

@CuiMao: Honestly, running Claude Code locally with LM Studio is surprisingly solid—RTX 5090 handles 64k context at 200+ tokens/s.

Submit Feedback