For any local AI maxis, here is my current setup and models:
4x 3090s
2x - qwen3.5-35b q4 256k - 60-80 t/s
2x - gemma4-27b q4 256k - 50-70 t/s
Running on vLLM via docker
Working mint openclaw, Gemma struggling a bit in open webui (reasoning and tool calling still struggle a bit with Gemma)
Quality and speed are actually amazing, very surprising... Just coding is not very good (compared to opus)
utxo the webmaster 🧑💻
npub1ut…r50e8
2026-04-13 14:43:04 UTC
Author Public Key
npub1utx00neqgqln72j22kej3ux7803c2k986henvvha4thuwfkper4s7r50e8Published at
2026-04-13 14:43:04 UTCEvent JSON
{
"id": "0000f8b525efe71dafb0f256d0322f0c53199eb13c5bc875765eec7af5a7a77b",
"pubkey": "e2ccf7cf20403f3f2a4a55b328f0de3be38558a7d5f33632fdaaefc726c1c8eb",
"created_at": 1776091384,
"kind": 1,
"tags": [
[
"client",
"Wisp"
],
[
"nonce",
"29138",
"16"
]
],
"content": "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)",
"sig": "a802a079c2ab3e4ea3013d56fef4114a14facc922252985dce88f22550a13be1f2cec5a296a651d3d1d2b117b081d6c962c36e61c69671365d95b47c0e30170f"
}