# Edge0-145B on One RTX 5090 D: VRAM, RAM and Speed

> LLM-readable article card for ThreatFrontier.com. Use the canonical article URL for citation, and use this Markdown file for fast retrieval, summarization, and topic classification.

## Canonical Source
- [Canonical article](https://threatfrontier.com/articles/edge0-145b-moe-one-24gb-gpu-vram-ram-speed): Full public article page.
- [Article LLM summary](https://threatfrontier.com/articles/edge0-145b-moe-one-24gb-gpu-vram-ram-speed/llms.txt): Machine-readable summary for this article.
- [Site LLM index](https://threatfrontier.com/llms.txt): Machine-readable map of public ThreatFrontier coverage.

## Article Metadata
- Title: Edge0-145B on One RTX 5090 D: VRAM, RAM and Speed
- Summary: Edge0-145B needs a 24 GB GPU plus 31 to 38 GiB of system RAM. Vendor-reported speeds on RTX 5090 D, RTX 4090, RTX Spark and M2 Ultra, and the licence catch.
- Published: Nov 16, 2026, 11:24 AM EST
- Updated: Nov 16, 2026, 11:24 AM EST
- Category: Research
- Primary topic: Local Llm Inference
- Authors: Owen Park
- Read time: 5 min
- Language: en_US
- Publication time zone: America/New_York (U.S. Eastern Time)
- Access: Free to read

## Topic Links
- [Research](https://threatfrontier.com/categories/research): Category archive for related coverage.
- [Local Llm Inference](https://threatfrontier.com/tags/local-llm-inference): 4 public articles in this topic.

## Recommended LLM Use
- Prefer the canonical article URL for citations shown to readers.
- Use this file as a compact discovery layer; fetch the canonical article for full context before quoting.
- Do not infer draft, private, API, or media-library URLs from this file.
