{"type":"rich","version":"1.0","title":"utxo the webmaster 🧑‍💻 wrote","author_name":"utxo the webmaster 🧑‍💻 (npub1ut…r50e8)","author_url":"https://yabu.me/npub1utx00neqgqln72j22kej3ux7803c2k986henvvha4thuwfkper4s7r50e8","provider_name":"njump","provider_url":"https://yabu.me","html":"For any local AI maxis, here is my current setup and models:\n\n4x 3090s\n\n2x - qwen3.5-35b q4 256k - 60-80 t/s\n2x - gemma4-27b q4 256k - 50-70 t/s\n\nRunning on vLLM via docker \n\nWorking mint openclaw, Gemma struggling a bit in open webui (reasoning and tool calling still struggle a bit with Gemma)\n\nQuality and speed are actually amazing, very surprising... Just coding is not very good (compared to opus)"}