Comments (15)

• @thelibertariantraveler ♥ 9 2026-05-11

  Why no use jan, anythingLLM, Ollama or LM Studio ?! Also running AI is one thing, the TPS is another. If you have 0.5 tokens per second it is impossible to work with. That's why most people use VRAM or unified ram

• @jackyproquo ♥ 3 2026-05-13

  Guys I open sourced the entire human knwoledge in a floppy disk so we can use old tech again pls follow

• @alexmansuroglu ♥ 1 2026-05-11

  Ai

• @stratashi 2026-05-16

  Ai

• @gianf_lavoratti 2026-05-11

  AI

• @its_minhnguy 2026-05-11

  AI

• @holamandini 2026-05-11

  AI

• @z_a_b_u 2026-05-11

  AI

• @bzzerra 2026-05-11

  AI

• @ale.__._x 2026-05-11

  Ai

• @jmbecedas 2026-05-11

  AI

• @schiefi_hh 2026-05-11

  AI

• @dejy_cro 2026-05-11

  AI

• @it_s_ivan_ 2026-05-11

  AI

• @gtrza43 2026-05-11

  Ai