LunarCrush LLM | creator/twitter::1886394417654677504/posts

[GUEST ACCESS MODE: Data is scrambled or limited to provide examples. Make requests using your API key to unlock full data. Check https://lunarcrush.ai/auth for authentication information.]

[@moskstraum21745](/creator/twitter/moskstraum21745)
"@ollama @nvidia @NVIDIAAI @NVIDIA_AI_PC Crappy memory bandwidth. Even M1 Max from 2022 beats it badly"  
[X Link](https://x.com/moskstraum21745/status/1978080359783727149) [@moskstraum21745](/creator/x/moskstraum21745) 2025-10-14T12:48Z XX followers, XXX engagements


"@wightmanr @TheZachMueller @MrCatid Apple probably wanted to DIY because they understood that Pytorch developer had near-zero interest in decent Apple silicon support. Don't forget that M has been launched in 2020 more than three years before MLX. Pytorch MPS is still gravely wanting as of today"  
[X Link](https://x.com/moskstraum21745/status/1981431302369746981) [@moskstraum21745](/creator/x/moskstraum21745) 2025-10-23T18:43Z XX followers, XX engagements

[GUEST ACCESS MODE: Data is scrambled or limited to provide examples. Make requests using your API key to unlock full data. Check https://lunarcrush.ai/auth for authentication information.]

@moskstraum21745 "@ollama @nvidia @NVIDIAAI @NVIDIA_AI_PC Crappy memory bandwidth. Even M1 Max from 2022 beats it badly"
X Link @moskstraum21745 2025-10-14T12:48Z XX followers, XXX engagements

"@wightmanr @TheZachMueller @MrCatid Apple probably wanted to DIY because they understood that Pytorch developer had near-zero interest in decent Apple silicon support. Don't forget that M has been launched in 2020 more than three years before MLX. Pytorch MPS is still gravely wanting as of today"
X Link @moskstraum21745 2025-10-23T18:43Z XX followers, XX engagements