#oogabooga — Public Fediverse posts

Y'all. My solar powered Hermes debugged itself. SpeechToText was broken. Turns out VRAM was full because I made the LLM context bigger, so the STT model couldn't load. In the end, I used a smaller model and put it back on GPU, but check out what Hermes did autonomously when I told it to fix itself:

-The AI found that the system's GPUs were completely out of memory, causing the local speech-to-text tool to crash.
-It switched the setting to use the CPU instead.
-The change failed at first because the underlying code ignored the new setting.
-The AI located and fixed these bugs, updated the code to correctly read the CPU setting, and restarted the system.
-After reloading, the system successfully transcribed voice messages.

Folks, LLMs may not be "intelligent" but they're capable at specific tasks. I checked Hermes code on Github and found this actual bug is real !!

#solarai #decentralized #smarthome #homeassistant #hermes_agent #oogabooga #LocalAI #SelfHosted #Homelab #BudgetBuild, #HardwareHacking

The local solar powered AI server is tweaked pretty good - the 3x 2080 ti being able to pull near 750w is literally all 3 at max power combined. All on DDR3/PCIe3. And folks told me it would be slow 😆 Qwen3.6-35B-A3B-UD-Q4_K_M.gguf is the model of choice for now, and grants a 256k context window.

#solarai #decentralized #smarthome #homeassistant #hermes_agent #oogabooga #LocalAI #SelfHosted #Homelab #BudgetBuild, #HardwareHacking

The solar powered LLM server seems to be happy with Qwen3.6-35B-A3B-UD-Q4_K_M. It gets around ~72 tokens per second and costs me $0.00 per token.

And the server itself is an ancient DDR3 platform with 3 2080 ti GPUs in it!

#solarai #decentralized #smarthome #homeassistant #hermes_agent #oogabooga #LocalAI #SelfHosted #Homelab #BudgetBuild, #ComfyUI #HardwareHacking #ai #llm #llms

So, I stumbled upon the fact that Hermes Agent has an OpenAI endpoint API. This allowed me to directly substitute Hermes in as my Home Assistant LLM. Now they interact seamlessly. Now my Home has a "brain". Uh oh. 🤣

Solar powered local AI server spec:
* Intel Core i7-3930K CPU
* Gigabyte GA-X79-UD5 Motherboard
* 64GB DDR3 RAM (8 x 8GB G.Skill Ripjaws X)
* 3 x NVIDIA GeForce RTX 2080 Ti Blower Edition GPUs (33GB Total VRAM)
* Corsair RM1000e 1000W Power Supply
* 240GB SATA SSD (OS Boot Drive)
* 3 x 1TB SATA SSDs (AI Storage Array)
* Advantech Industrial Computer 510 Case

#solarai #decentralized #smarthome #homeassistant #hermes_agent #oogabooga #LocalAI #SelfHosted #Homelab #BudgetBuild, #ComfyUI #HardwareHacking

The solar powered local AI server + Home Assistant + Hermes Agent is blowing my mind. Yesterday it wrote the script for another lamp using the same simple prompts.

#localai #solarai #decentralized #smarthome #homeassistant #homelab #hermes_agent #oogabooga