Daniel Wigton on Nostr: I get about 3.5 tokens/sec. A 5090 is tempting simply because it would cut RAM bound ...
I get about 3.5 tokens/sec. A 5090 is tempting simply because it would cut RAM bound performance in half.
Published at
2025-03-25 18:20:20Event JSON
{
"id": "c72d74b91ad005e2a96a280ace21911b0dd466505ec4e420a462be5d0bf08503",
"pubkey": "75656740209960c74fe373e6943f8a21ab896889d8691276a60f86aadbc8f92a",
"created_at": 1742926820,
"kind": 1,
"tags": [
[
"e",
"0808d872c5db2df9223b86c0a1ac5ef13960cb8123502c7d7259b1ec72f233aa",
"",
"root"
],
[
"e",
"d9b37a7a1dc0c16022115b05972d1c8822d9042999b1c1b9a9c49afc19dbfc28",
"",
"reply"
],
[
"p",
"32e1827635450ebb3c5a7d12c1f8e7b2b514439ac10a67eef3d9fd9c5c68e245"
],
[
"p",
"75656740209960c74fe373e6943f8a21ab896889d8691276a60f86aadbc8f92a"
]
],
"content": "I get about 3.5 tokens/sec. A 5090 is tempting simply because it would cut RAM bound performance in half.",
"sig": "4173c7499e8decb9c8ed0b4b62900aaf6c16714241ab294e2337353e5fa8ad33cf264bddf2d3236a9465224e93aca552824567c250eb9f1155c2c83811c64391"
}
