Urgent.News

What's breaking now, across thousands of outlets.

AI

One-slot, low-profile Nvidia RTX 3060 12 GB with two monitor outputs breaks cover at Newegg for $496 — bus-powered model looking for a use case in local LLM work

Small-form-factor, low-profile Nvidia RTX 3060 12 GB with two monitor outputs breaks cover at Newegg for $496 — bus-powered model looking for a use case in local LLM work

One-slot, low-profile Nvidia RTX 3060 12 GB with two monitor outputs breaks cover at Newegg for $496 — bus-powered model looking for a use case in local LLM work

Nvidia has reintroduced the RTX 3060 with a 12 GB version, featuring a low-profile design suitable for compact systems. This one-slot card, priced at $495.59 by SRhonyra, draws power solely from the PCIe slot, eliminating the need for a robust power supply and reducing cable clutter. Designed for entry-level local AI workstations, it can run 7B to 13B language models, despite drawing only 70 W of power from the PCIe slot, resulting in slightly lower performance compared to its full-sized counterparts.

Despite the reduced power, the card's low-profile design and minimal power consumption make it an attractive option for those seeking a compact solution for running larger models in constrained environments.

Written by urgent.news from Tom's Hardware's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.

This story

This is one outlet's version. Read the fullest account.

Read the original at tomshardware.com →

More in AI

Stealing AI Reasoning Traces

Interesting research: “ Stealing Reasoning Traces from Proprietary LLM APIs “: Abstract: Leading large language model providers now conceal their models’ step-by-step reasoning, or chain-of-thought…

  • Proprietary LLM providers conceal reasoning steps as encrypted blocks.
  • Researchers discovered interchangeable encrypted reasoning blocks across sessions and models.

More from Tuesday 8 September →