Live and recent posts from across the Fediverse tagged #hermesagent, aggregated by home.social.
Now that I have TWO LLM servers, one for fast response, one for accurate detailed response. Hermes can use either one whenever it wants.
The main site: https://lydie.cc/solar-ai-serverv2.html
But the cool one is the website I had Hermes and the P100 server create using Strata's QWEN3.8 120B apparatus:
My personal data center runs my Hermes/Home Assistant, and is not used to generate slop.
#AI #homelab #homeassistant #llm #hermesagent #selfhosted #selfhosting
Got Strata hitting the GPUs hard via Hermes Agent #llm #localai #homelab #Strata #hermesagent
hermes-agent v0.22.1
Add nemotron super 3.5 default parameters to the agent; Add a curated model list at the top of the model picker in the CLI; Add hermes-lang-ko, a Korean Desktop language pack, to the plugin catalog; Add hermes-lang-pt-br, a Brazilian Portuguese language pack, to the plugin catalog; Add teamorouter…
RT @NousResearch: Hermes Agent v0.22.0: Die Schwellenwert-Veröffentlichung
mehr auf Arint.info
#Changelog #HermesAgent #Release #SoftwareUpdate #TechNews #Version22 #arint_info
🚀 New #release · hermes-agent v0.22.0
- Guided setup chat for new users, no API key needed.
- Connectors for apps, no account required to start.
- One-click local models with llama.cpp runtime.
- Stable releases, signed packages, and unified package manager.
Details, install & alternatives → https://selfhost.directory/project/hermes-agent#update-21654765
Meet SolarAI LLM Server V2, now complete. Probably the world's first quad GPU, DDR3 based rig using HDDs for LLM storage that generates 33.4 tps with the Strata QWEN3.8-120b model, and it cost me about a grand USD.
This is the hardware/software stack:
-Asus Z9PE-D16 motherboard
-CPU: 2x Intel Xeon E5-2620 V2 Processor
-GPU: FOUR NVIDIA Tesla P100 16GB PCIe (64GB VRAM)
-RAM: 128GB DDR3
-Storage: 120GB SSD for OS
-Storage: FOUR 500GB WD Velociraptor HDDs for models
-OS: ubuntu-24.04.5 server amd64
-CUDA 12 for Pascal
It will run my Hermes/Home Assistant, and is not used to generate slop.
#AI #homelab #homeassistant #llm #hermesagent #selfhosted #selfhosting