Tag DGX Spark

AI & Compute

Qwen 3.8 27B Needs Two RTX 5090s for Full Context

Three horizontal bars drawn to scale from one shared axis: two short gray bars for the 32,768 and 37,740 tokens of context a single RTX 5090 reached under the published vLLM and SGLang recipes, against a blue bar roughly eight times longer for Qwen 3.8 27B's full 262,144-token window.

Weights that fit in 32GB still left the RTX 5090 waiting half an hour for a first token, and the fix was a different inference engine rather than a different card.

Saya
September 9, 2026

Drivers & Software

A Legion Go BIOS Is Bricking Handhelds, and NVIDIA Joins the Linux Firmware Pipeline

A four-layer update stack with the bottom firmware layer in red, the one level where a failed flash costs the whole machine.

Owners report Lenovo's N3CN42WW BIOS leaving first-generation Legion Go handhelds unbootable, NVIDIA becomes the fourth premier sponsor of LVFS, and Proton 11.0-2 lands as a release candidate.

Saya
August 6, 2026