Lenovo releases new 15-inch gaming laptop internationally with 48 GB VRAM and 1,100 nit OLED display

[Redaktion]

Lenovo has finally released its 15-inch gaming laptop powered by AMD Strix Halo processors. Sold internationally, the Legion 7a 15ASH11 combines Radeon 8060S graphics with a 165 Hz OLED display, an 84 Wh battery and dual M.2 slots. The laptop can configure up to 48 GB VRAM too, thanks to optional 64 GB RAM variants.

https://www.notebookcheck.net/Lenovo-releases-new-15-inch-gaming-laptop-internationally-with-48-GB-VRAM-and-1-100-nit-OLED-display.1305283.0.html

[48gb vram]

48gb vram? So 2 rtx 5090m ?

[yes]

48gb vram? So 2 rtx 5090m ?

In terms of pure allocate-able memory, yes, may even be slightly more than 2 rtx 5090m (because the OS is in the other 16 GB of memory).

In terms of FPS, it's a Strix Halo APU, so it's comparable to a 4060 Mobile:
3dmark.com/search - Steel Nomad:
Radeon 8060S: Average score: 2031
RTX 5050 (notebook): Average score: 2124
RTX 4060 (notebook): Average score: 2262

In terms of memory bandwidth:
Strix Halo: 256 GB/s (=256-bit * 8000MT/s / 1000 / 8)
RTX 5050 (notebook): 384 GB/s (en.wikipedia.org/wiki/GeForce_RTX_50_series#Mobile)

AMD advertises Strix Halo mainly for AI, and while a 128 GB RAM Strix Halo will fit a bigger LLM, its prompt processing speed will be that of a 4060 (notebook)/5050 (notebook) and its token generation speed will be that of 4060 Laptop (256 GB/s).
AI, both for training and inferencing for the endconsumer requires these 3 things:
1. Memory size, to fit a decently capable LLM.
2. Memory speed, also known as bandwidth, relevant for token generation (output) speed.
3. GPU compute, relevant for prompt processing (input) speed.
Prompt processing: The larger the input, the faster the GPU you'd need, especially for agentic workflows. The prompt processing speed is based on GPU' FPS number in games/3D benchmarks.
(The number of CPU threads doesn't matter for running AI (aka inferencing) (4 threads pretty much tops-out a dual-channel PC))

[RobertJasiek]

AI, both for training and inferencing for the endconsumer requires these 3 things:

More than 3. E.g., also CPU cores / threads / kinds, CPU single thread speed, CPU multi-thread speed, GPU driver, GPU libraries...

[PSREF uploaded]

psref.lenovo.com/l/Product/Legion/Legion_7_15ASH11