> A huge benefit of local setups at our studio is that a lot of our software can't run headless, so when we're having agents work in Blender or in Unity etc with MCP that'd otherwise eat up our normal computer use
I'm curious about your setup. I've been tinkering with the idea of setting up Blender (cli use) in a container to allow agents to verify the scripts they are generating compile at a minimum. One thing I've found extremely helpful was generating a RAG of the current version of Blender.
For anyone wondering, I'm running Gemma4 26b A4B on a mini PC with 32 GB of DD4 and a Vega 7 iGPU (llama.cpp w/ Vulkan).
You can buy most ATX (or derivative) cases and have an adapter bracket printed from services like JLPCB. Make sure the material is ABS or another high temperature plastic to resist heat warp.
2.4GHz is already incredibly crowded and prone to interference (in urban environments). I remember once picking up emissions on a Bluetooth headset from a leaky microwave oven.
Are you using the stock cooler? I’m going with an AIO for the APU, but I worry that the little heatsinks I’m planning for the VRMs aren’t going to cut it.
I assume you’re talking about the n52 vs n20. I’ve had both engines as daily drivers, and they’re both fine. The n20 has a bad rap due to early models failing from a timing chain guides breaking.
I second that recommendation. It's my favorite part of the Louvre. It's a very castle-looking castle; it feels like it's straight out of a movie.
To my mind, all of the best stuff in the Louvre is in the basement: the Codex Hammurabi, Babylonian artifacts, etc. Yeah, it's all just as stolen as the artifacts in the British Museum that get more attention, but it's more significant than their art collection that are "the greatest" because they said so.
(Not that they aren't also great works. But there are many great works, and the distinction of these has more to do with French nationalism than any serious consideration of artistic merit.)
I'm curious about your setup. I've been tinkering with the idea of setting up Blender (cli use) in a container to allow agents to verify the scripts they are generating compile at a minimum. One thing I've found extremely helpful was generating a RAG of the current version of Blender.
For anyone wondering, I'm running Gemma4 26b A4B on a mini PC with 32 GB of DD4 and a Vega 7 iGPU (llama.cpp w/ Vulkan).
reply