DeepSeek compared running locally - various model sizes and quantizations on M1, M2, M3, M4 Max MacBooks. ๐ Gear Links ๐ * ๐ช๐ช Favorite knife: https://amzn.to/3zIYrkZ * ๐๐ฅ Oculink dock: https://amzn.to/3Na7s9F * ๐ป๐ Mini PC with 32GB RAM: https://amzn.to/3ZJEwNs * ๐ ๏ธ๐ My RTX4090: https://amzn.to/3zRMmtG * ๐งโก Power supply 1200W: https://amzn.to/3Ya7WDh * ๐ ๏ธ๐ 96GB RAM kit: https://amzn.to/3ZhQ4qR * ๐งโก Great 40Gbps T4 enclosure: https://amzn.to/3JNwBGW * ๐ ๏ธ๐ My nvme ssd: https://amzn.to/3YLEySo โจ๏ธ๐ข Keyboard: https://www.keychron.com/products/keychron-q1-max-qmk-via-wireless-custom-mechanical-keyboard?ref=azisk * ๐ฆ๐ฎ My gear: https://www.amazon.com/shop/alexziskind ๐ฅ Related Videos ๐ฅ * ๐ RAM torture test on Mac - https://youtu.be/l3zIwPgan7M * ๐ ๏ธ FREE Local LLMs on Apple Silicon | FAST! - https://youtu.be/bp2eev21Qfo * ๐ ๏ธ Set up Conda - https://youtu.be/2Acht_5_HTo * ๐ค INSANE Machine Learning on Neural Engine - https://youtu.be/Y2FOUg_jo7k * ๐ ๏ธ Developer productivity Playlist - https://www.youtube.com/playlist?list=PLPwbI_iIX3aQCRdFGM7j4TY_7STfv2aXX ๐ AI for Coding Playlist: ๐ - https://www.youtube.com/playlist?list=PLPwbI_iIX3aSlUmRtYPfbQHt4n0YaX0qw โ โ โ โ โ โ โ โ โ โค๏ธ SUBSCRIBE TO MY YOUTUBE CHANNEL ๐บ Click here to subscribe: https://www.youtube.com/@AZisk?sub_confirmation=1 โ โ โ โ โ โ โ โ โ Join this channel to get access to perks: https://www.youtube.com/channel/UCajiMK_CY9icRhLepS8_3ug/join โ โ โ โ โ โ โ โ โ ๐ฑ ALEX ON X: https://twitter.com/digitalix #deepseek #llm #macbook

Three months wrong about why my 4-node AMD cluster was slow
112.2K views

I just gave Claude BEAST mode ๐คฏ ... Images and video!
43.7K views

This Local LLM Looked Smart Until I Saw What It Made Up
81.3K views

I Plugged a DGX Spark and Mac Together... and Didnโt Expect This
230.0K views

Everyone is Scalping Mac Minis for OpenClawโฆ Hereโs the Workaround
68.4K views

I Tested the $500 MacBook Neoโฆ Iโm Shocked
117.6K views