Try running Llama 3.2 1B Q8, Llama 3.2 3B Q8 & Stable Diffusion 1.5 on Intel UHD Graphics 630. Also, try to run AI models on the CPU.
https://juantechblog.github.io/posts/run-local-llm-stable-diffusion-locally-low-end-hardware/
#AI #llm #stablediffusion #vulkan #avx2 #igpu
Juan /
npub1qw…8qnlv
2024-10-31 07:10:16
Author Public Key
npub1qw2nttuetnrcwqvy9rdfyxk7yspyljzsmj3nrq35pctymschvg8sl8qnlvSeen on
wss://relay.nostr.bandPublished at
2024-10-31 07:10:16Event JSON
{
"id": "966fafbf5ec2200b9babd6421c1a1e1a2e142387e6299e255d8fd44664c20dc0",
"pubkey": "039535af995cc787018428da921ade24024fc850dca33182340e164dc317620f",
"created_at": 1730358616,
"kind": 1,
"tags": [
[
"t",
"ai"
],
[
"t",
"llm"
],
[
"t",
"stablediffusion"
],
[
"t",
"vulkan"
],
[
"t",
"avx2"
],
[
"t",
"igpu"
],
[
"proxy",
"https://mastodon.social/users/JuanJuanJuan/statuses/113400782313907087",
"activitypub"
]
],
"content": "Try running Llama 3.2 1B Q8, Llama 3.2 3B Q8 \u0026 Stable Diffusion 1.5 on Intel UHD Graphics 630. Also, try to run AI models on the CPU.\n\nhttps://juantechblog.github.io/posts/run-local-llm-stable-diffusion-locally-low-end-hardware/\n\n#AI #llm #stablediffusion #vulkan #avx2 #igpu",
"sig": "173ba1edba108df9d0594b1673933eb5d9153932c1ca5569b2dce5d7733f6192339f1413b26b403b9b89f6ee8b456c404ce4c217bf8fcc249f56797900e6a121"
}