Daniel Wigton on Nostr: Which model? So far llama3.3 is my only tolerable local model. But it is throttled by ...
Which model? So far llama3.3 is my only tolerable local model. But it is throttled by the speed my ram can feed the remaining 18GB to my CPU. So mostly I talk to my CPU I guess even though the GPU is doing 4/7 of the work.
Published at
2025-03-25 18:17:31Event JSON
{
"id": "d9b37a7a1dc0c16022115b05972d1c8822d9042999b1c1b9a9c49afc19dbfc28",
"pubkey": "75656740209960c74fe373e6943f8a21ab896889d8691276a60f86aadbc8f92a",
"created_at": 1742926651,
"kind": 1,
"tags": [
[
"e",
"0808d872c5db2df9223b86c0a1ac5ef13960cb8123502c7d7259b1ec72f233aa",
"",
"root"
],
[
"p",
"32e1827635450ebb3c5a7d12c1f8e7b2b514439ac10a67eef3d9fd9c5c68e245"
]
],
"content": "Which model? So far llama3.3 is my only tolerable local model. But it is throttled by the speed my ram can feed the remaining 18GB to my CPU. So mostly I talk to my CPU I guess even though the GPU is doing 4/7 of the work.",
"sig": "5c35f370f2e55a7ab5963dd409954f715b795100604b034d624043646d205c885258a64f94154f6975a9cd9476f1f0d010c86b3d468f86c986587f7355744182"
}
