> Finding it's much easier to migrate to linux with an llm as a troubleshooting assistant.
Especially with NixOS. I would never allow an LLM to make core updates to my OS for fear of breaking it. Now LLMs manage all my packages and upgrades, and because it's all declarative, I can always revert anything that goes wrong.
For high concurrency, using the blackwell's native native W4A4 MLP compute path, nvfp4 is something like a 1.2-1.5x performance increase over FP8. We're doing data enrichment (so, tasks completed successfully + tokens/second) so the performance bump shows up in the tasks/month number.
I am just now getting the benchmarks running against 3.8 27b but I expect similar results from benching 3.6 27b at the same quant.
I didn't have time to run this as well, but we're getting a 99% agent completion rate across all tasks and 98% task decision that matches the human selected option(s) on Qwen 3.8 27B @ NVFP4. There may be a difference between FP8 and NVFP4 but it's inconsequential for our data enrichment purposes.
Especially with NixOS. I would never allow an LLM to make core updates to my OS for fear of breaking it. Now LLMs manage all my packages and upgrades, and because it's all declarative, I can always revert anything that goes wrong.