HN Explorer

utopman

↗ HN profile [ 46.1 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. Show HN: Best setup local LLM found for a 5090 (llama.cpp fork + turboquant) (local-llm.utop.workers.dev)

    Hi folks, I found this setup on consummer hardware that seems to have great results on local hardware. - qwen 3.6 q6 - 450 K context using turboquant turbo3 mode llama.cpp fork - multimodal support This AI generated…

    2 points 1
  2. Ask HN: Consumer grade hardware AI sound / music generation models

    Hi folks, I look for some open / free to use (commercial products) generated sound / music AI generation tool that I can run locally on common consummer hardware. I would like to iterate faster on prototyping apps /…

    1 points 0
  3. Ask HN: What Happened to Noiselith

    Hi folks. Few month ago, I found a desktop local first software to generate image from prompts using my gpu. It's called noiselith. Today it has completely gone from what I can find on internet and I have no clues why.…

    1 points 0
  4. 1 points 1
  5. Show HN: Chat GPT TUI (github.com)

    Here is a tool to ask chat gpt using a personal token in an interactive TUI tool with context between interactions and color highlighting for code samples. I found it very useful since I made it, so I share it here in…

    3 points 2
  6. I Finnished Google Twice (youtube.com)
    2 points 3
  7. Ask HN: I wonder if message length have impact on communication efficiency

    I look for studies that discuss about messages lengths and communication efficiency and the relation if any with nowdays messaging usages compared with previous generation habits. Any thoughts, sourcesor suggestions are…

    2 points 4
  8. Ask HN: Dynamic lowering “fast” graphic settings in games : Save a panda !

    GTA V does it good : when ingame hardware is used at maximum capacities, when game menu open (pause / escape) hardware (GPU / CPU) consumption is 3-10 times lower and when game is alt-tabed, hardware consumption is near…

    2 points 1