alphakamp on Nostr: In my experiments, I am painfully frustrated with the hardware on hand for AI. ...
In my experiments, I am painfully frustrated with the hardware on hand for AI. Ollama, LMstudio, Jan, gpt4all. Let's say 30 tokens max with 8b. Tried out some basic local docs stuff with a single PDF/CSV, most 8b models can even read a basic spreadsheet without failing miserably
Published at
2025-02-02 00:13:06Event JSON
{
"id": "bbfe1f00d4ea4c298baa907dcf099221369839ac22d49aa85ac72d0dc323859e",
"pubkey": "cc53f373a72a82b7fb07d6efd6c8f07b32316e4ede4f9cfa908449554ff2ada5",
"created_at": 1738455186,
"kind": 1,
"tags": [],
"content": "In my experiments, I am painfully frustrated with the hardware on hand for AI. Ollama, LMstudio, Jan, gpt4all. Let's say 30 tokens max with 8b. Tried out some basic local docs stuff with a single PDF/CSV, most 8b models can even read a basic spreadsheet without failing miserably",
"sig": "cf1dd21f570aa5bdbe92e47d44e3dc8a3c111f23312650730c489e05c8510cf10f2c0e1568c0e7d789b4ca2992f7059437e3c3789eb648777f409640d8b03be4"
}