AJ(@ItsmeAjayKV):Local AI has got to a point now i cannot imagine a life without it. I want it in every device i own. And as a result it has ruined how i shop or even plan for tech iphone or android? i'm checking the RAM Mac? Unified memory GPU? VRAM Every upgrade i'm considering now has to fit bigger models, low memory devices barely make the shortlist anymore. And now i'm checking how fast those models will run, too. Anyone else stuck in this rabbit hole? (image generated by Qwen-image-2.1 running locally on my 3090 🍻)

@ItsmeAjayKV

Bullish on local AI LLM finetuning, quants, repe, llama.cpp Jobless atm! 1x 3060, 1x 3090: 64GB RAM N4 (日本語勉強中) 🎌

参加 September 2016

767 フォロー中 7.7K ファン

AJ@ItsmeAjayKV

2026.09.21 14:58

Local AI has got to a point now i cannot imagine a life without it. I want it in every device i own. And as a result it has ruined how i shop or even plan for tech iphone or android? i'm checking the RAM Mac? Unified memory GPU? VRAM Every upgrade i'm considering now has to fit bigger models, low memory devices barely make the shortlist anymore. And now i'm checking how fast those models will run, too. Anyone else stuck in this rabbit hole? (image generated by Qwen-image-2.1 running locally on my 3090 🍻)