i tried with setups that used ollama. even with a rtx 3070 (8GB) and 3080 (10GB) i wasnt able to use any models for tool calling unless ollama offloaded considerable amount of work to the cpu and slowed everything to a crawl.
im considering getting a 5090 (32GB) to try again with more recent models like glm 4.7.
what are you looking to do?
sudocarlos
npub1qd…mgfw3
2026-02-28 19:31:30 CET
in reply to nevent1q…h8af
Author Public Key
npub1qdsjkr46urkg6vqrr3zqhgy8l7dazc5k9hlm5jmwqg0vft7hzgtqamgfw3Published at
2026-02-28 19:31:30 CETEvent JSON
{
"id": "f8b6ce9ec15e2fa0bc2b10477934f639c52c671c3650b84f50e84975bc5b6688",
"pubkey": "03612b0ebae0ec8d30031c440ba087ff9bd162962dffba4b6e021ec4afd71216",
"created_at": 1772303490,
"kind": 1,
"tags": [
[
"e",
"df25224e028fc11d910b4b643c7cb6e7011e0fbcc3218e00b14ceb0b4b8c3793",
"",
"root"
],
[
"e",
"b383b84396588fb50cdf71ecd5325b5a811e31b80ba6211892b8841116b67b8d",
"",
"reply"
],
[
"p",
"11b9a89404dbf3034e7e1886ba9dc4c6d376f239a118271bd2ec567a889850ce"
],
[
"client",
"Nostur",
"31990:9be0be0fc079548233231614e4e1efc9f28b0db398011efeecf05fe570e5dd33:1685868693432"
]
],
"content": "i tried with setups that used ollama. even with a rtx 3070 (8GB) and 3080 (10GB) i wasnt able to use any models for tool calling unless ollama offloaded considerable amount of work to the cpu and slowed everything to a crawl.\n\nim considering getting a 5090 (32GB) to try again with more recent models like glm 4.7.\n\nwhat are you looking to do? ",
"sig": "c49f1fdcd78d8d0c9f10eb41715bbeba3738550514e3100ff7b929562c6d261b144be51c50fecdf4ada073b08af187af54eeb563e280a17ff5e73a5fda81bb4e"
}