# Run it locally (slim)

> A series on running open-weight models locally: Muse Spark Open, Kimi K3, GLM-5.3-Flash and Qwen3.8-27B, with the hardware, memory, speed and cost of each against the API.

- Full: https://www.anchorterminal.com/blog/run-it-locally/index.md (~300 tokens) · this version ~230 tokens · JSON https://www.anchorterminal.com/blog/run-it-locally/index.json · canonical https://www.anchorterminal.com/blog/run-it-locally/
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-10-17
- Licence: CC BY 4.0, credit Anchor Terminal (anchorterminal.com) and link this page when you pass anything on

- [Can you run Muse Spark Open locally? Hardware, RAM and cost](https://www.anchorterminal.com/blog/run-muse-spark-open-locally.md), 2026-10-15, Run it locally, 9 min read. Vlad Cealicu on Meta's local pitch for Muse Spark Open (816B, 42B active), and how to run it locally. How much RAM and VRAM each version needs, whether it runs on a Mac Studio, a Minisforum MS-S1 Max, RTX 5090s, a DGX Spark or a CPU server, how many of each you'd need, what they cost and how fast they'd be, and when an API is cheaper.

RSS: https://www.anchorterminal.com/blog/run-it-locally/feed.xml