On-device generative machine learning models are coming to Macs.
Apple managed to squeeze a large language model into a MacBook Pro M2, it runs 25 times faster and models 2x larger, by storing the models in flash memory, made possible on M chips.
https://arxiv.org/pdf/2312.11514.pdf
jingles / Jingles
npub1al…86dsn
2024-01-31 02:02:27
Author Public Key
npub1alpha9l6f7kk08jxfdaxrpqqnd7vwcz6e6cvtattgexjhxr2vrcqk86dsnPublished at
2024-01-31 02:02:27Event JSON
{
"id": "d326fb21b912c918c1f312e9512b2786d16a77950e7ab3b31441289f57a7e6aa",
"pubkey": "efc37e97fa4fad679e464b7a6184009b7cc7605aceb0c5f56b464d2b986a60f0",
"created_at": 1706666547,
"kind": 1,
"tags": [
[
"r",
"https://arxiv.org/pdf/2312.11514.pdf",
"page"
],
[
"r",
"arxiv.org",
"host"
]
],
"content": "On-device generative machine learning models are coming to Macs.\n\nApple managed to squeeze a large language model into a MacBook Pro M2, it runs 25 times faster and models 2x larger, by storing the models in flash memory, made possible on M chips.\n\nhttps://arxiv.org/pdf/2312.11514.pdf",
"sig": "a4196a951de9e9f54e7df0f77f24801c09ae506fc411dc53363f74f5769892ad4a4e8521edae888e859239f530d00d5ce6fe1e9b065d56e62908bc7166bc11df"
}