Lenovo releases new 15-inch laptop in the US with Ryzen AI Max+ 388 and 165Hz OLED display

[Redaktion]

The Lenovo Yoga Pro 7a Gen 11 is now available in the US starting at $2,569.99. Its Ryzen AI Max+ 388 processor and Radeon 8060S graphics should provide plenty of power for creative work and gaming, while the 84Wh battery and bright 165Hz OLED touchscreen make it a capable everyday laptop as well.

https://www.notebookcheck.net/Lenovo-releases-new-15-inch-laptop-in-the-US-with-Ryzen-AI-Max-388-and-165Hz-OLED-display.1365488.0.html

[T0t()]

Interestingly, Lenovo is not offering the 64GB RAM option available in other markets. That leaves buyers with 32GB of non-upgradeable memory

Since the total memory (RAM + VRAM) in this laptop does not go above 32 GB: If you care about using this laptop for AI extensively, know that with current SoTA AI LLM model Qwen3.6-35B-A3B[1], in its class size (only 3B active parameters = fast token generation), and its bang for the buck, 4-bit, quant, you will be restricted to about this amount of context:

.. I've come to the conclusion that (1) 32768 is the biggest context I can get away with in an adequately smart model, and (2) it just ain't enough.

More about running AI models locally: notebookchat.com/index.php?topic=315954.0 ("Your own ChatGPT, offline: AI without the cloud on your laptop") and comments.

[1] artificialanalysis.ai/models/open-source?models=qwen3-6-27b%2Cqwen3-6-35b-a3b%2Cmuse-glimmer%2Cgemma-4-26b-a4b%2Cgemma-4-31b#artificial-analysis-intelligence-index (the dense 27B model is better, but it's much slower) (you can look up other models, or non-reasoning scores, in the table)
(Qwen3.8 release this week and will soon be added)

In this sense, any 32 GB RAM + 8 GB VRAM gaming laptop (used for 700-800 bucks) is superior.