Phi-4 + Bolt DIY + Cline & Aider : This 100% PRIVATE & LOCAL AI Coder is INSANE! (Beats Cursor!)

Поділитися
Вставка
  • Опубліковано 26 січ 2025

КОМЕНТАРІ • 46

  • @jimlynch9390
    @jimlynch9390 14 днів тому +21

    Thanks, I'm running phi4 on a 12 GB 3060. No problems so far. I don't think you need 16GB.

    • @MrVovsn
      @MrVovsn 14 днів тому

      More RAM more extra context length, am I wrong?

    • @MrMoonsilver
      @MrMoonsilver 14 днів тому

      You're right, more vram = larger contrxt

    • @Ren_Zekta
      @Ren_Zekta 14 днів тому +2

      @@MrVovsn it's 12 gb of VRAM, not RAM
      as for RAM, i have 32 gb and same 12 gb 3060, working great for me.

    • @fightlikabrave
      @fightlikabrave 14 днів тому

      Itll help though to have a 16g vram..the more vram, the better

    • @MrVovsn
      @MrVovsn 13 днів тому

      @@Ren_Zekta I am sorry, I meant VRAM of course.

  • @BanibrataDutta
    @BanibrataDutta 13 днів тому

    It's HF model card says that it is trained on a smallish set of python code files also limited to few modules. Good to see that, it can be used little more extensively.

  • @GarthScaysbrook
    @GarthScaysbrook 14 днів тому +2

    Thanks for the vid, keen to try Phi-4 :)

  • @sinayagubi8805
    @sinayagubi8805 14 днів тому +3

    what was your GPU? what was the model optimization? what tokens per second did you get?

  • @MonolopTR
    @MonolopTR 2 дні тому

    hi i cant run it on cline it always says i need spesicifation as i see you're using template named test phi 4 app can you please share it?

  • @연습용-j9t
    @연습용-j9t 10 днів тому +1

    Does it have the function as the same as composer in cursor?

    • @ArvindJuneja
      @ArvindJuneja 10 днів тому

      +1 am also curios

    • @showcaseshot
      @showcaseshot 10 днів тому

      I think so because I saw the compose icon on top but never used it it's just my assumption

  • @sinapxiagency
    @sinapxiagency 14 днів тому +4

    Hey King, do you hear about project dígits of nvidia, im trying to know if we can connect 3 of them to run locally a 600 b model parameter like deepseek

    • @sinayagubi8805
      @sinayagubi8805 14 днів тому +1

      btw, it has less flops than a 4090... but I am not sure what "peta flop at fp4 precision" means and what the precision of the 4090 was.

    • @breadles5
      @breadles5 14 днів тому

      ​@@sinayagubi8805 AI models operate using numerical precision, often adjusted through quantization. Higher precision involves using more bits per value, increasing memory usage and computational demands. By quantizing the model to lower precision, such as reducing from 32-bit to 16-bit or 8-bit representations, you can decrease memory and computational requirements. However, this reduction may lead to a slight decrease in model accuracy, offering a trade-off between resource efficiency and performance.
      It's important to note that the RTX 4090 does not natively support FP4 precision. Therefore, direct comparisons between a system operating at FP4 precision and the RTX 4090 are not straightforward. Lower precision formats like FP4 can significantly increase computational throughput, but they may also lead to reduced accuracy.

    • @vaingaler5001
      @vaingaler5001 14 днів тому +1

      I think it's better to wait for now until some people review the product. It might run deepseek v3 with 3 of them, but we don't know about the speed, like how many token/second it could run etc

    • @sinapxiagency
      @sinapxiagency 14 днів тому +1

      @@vaingaler5001 if can execute a deepseek v3 model, im sure that it will a success but lest wait

    • @MrMoonsilver
      @MrMoonsilver 14 днів тому +1

      Notnsure if you can cobble together three, he mentioned two in the keynote. Remains to be seen if that's the actual limit

  • @QuantumXdeveloper
    @QuantumXdeveloper 14 днів тому +1

    I have 4gb nvidia gtx 1650 gpu, may be that's why its not running. BTW thanks for the genuine review. Phi-4 looks so cool, hope that they might release the mini version of this too.

    • @Rusputin-eo6tv
      @Rusputin-eo6tv 13 днів тому

      it'll take at least 11.7 GB ram. You'll need to open other web tabs. So 12 is ok and 16 is optimal

    • @СергейПетров-ц3ъ
      @СергейПетров-ц3ъ 12 днів тому

      You can run any model on any computer. The only problem is speed. If you're memory is not enough then you can increase your swap

  • @scottx1415
    @scottx1415 14 днів тому

    That is pretty cool, haha
    Thanks

  • @teetanrobotics5363
    @teetanrobotics5363 14 днів тому

    Can you please playlists based on providers like Deepseek playlist, anthropic playlist, microsoft playlist, etc..

  • @syvern7197
    @syvern7197 14 днів тому

    what are the pc requirements for it?

  • @hammeedabdo.82
    @hammeedabdo.82 14 днів тому

    What is the best AI Coder?

  • @fairyroot1653
    @fairyroot1653 13 днів тому

    Still struggles with Strawberry challenge though

  • @Nodeagent
    @Nodeagent 14 днів тому

    how does it compare to deepseekv3 and claude3.5sonnet?

    • @aculz
      @aculz 13 днів тому

      not at all, its not comparable to both

    • @Nodeagent
      @Nodeagent 13 днів тому

      @ is it better or not as Clause at complex codebases?

  • @u007james
    @u007james 14 днів тому

    please do comparison between langraph vs bee framework

  • @PrinceIvannComiso
    @PrinceIvannComiso 14 днів тому

    Heh

  • @commie563
    @commie563 14 днів тому

    I have 2019 macbook 16 inch full spec
    Can I run this locally?