home.social

#omlx — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #omlx, aggregated by home.social.

fetched live
  1. I'm currently testing a few #LLM #MLX runtimes/apps on my #M5 Pro 24 GB. So far, I can't say which one gets the best performance out of a local LLM like #Gemma 4 12B.
    I've tested #Ollama, #LMStudio, #oMlx, and #osaurus. Each one has its own 1-2 tweaks that are supposed to squeeze out more performance.

    What's your experience been like?

    #Apple #MacBook #AI #localai #localllm

  2. I'm currently testing a few #LLM #MLX runtimes/apps on my #M5 Pro 24 GB. So far, I can't say which one gets the best performance out of a local LLM like #Gemma 4 12B.
    I've tested #Ollama, #LMStudio, #oMlx, and #osaurus. Each one has its own 1-2 tweaks that are supposed to squeeze out more performance.

    What's your experience been like?

    #Apple #MacBook #AI #localai #localllm

  3. schaut genau nach der richtigen mischung zwischen - wo man zu wenig einstellen kann - und - wo man zu viel einstellen kann :-P

    sehr aufgeräumtes design und guter erst eindruck - pinguin als logo vllt ein bissel zu selbstbewusst :D

    ich hab das bisher so gelöst: lmstudio hört auf 0.0.0.0 - ist mit verbunden mit vserver - caddy auf vserver stellt mein lmstudio über https in netz

    so kann ich von überall meinen lokaken llm aufrufen

    ist dann noch ??? wohl eher :)

  4. Never thought that I could do this on my Mac

    #oMLX #LocalLLM

  5. Hermes Agent + oMLX = Caching-aware agent harness on macOS

    Claude Code’s source code leak revealed a huge gap in context management and cache-awareness comparing to its open-source alternatives like OpenCode.

    Hermes Agent is doing a better job at these among the “claws” ATM.

    hermes-agent.nousresearch.com

    mastodon.tevinzhang.com/@tevin

    #HermesAgent #oMLX #ClaudeCode #OpenCode

  6. Hermes Agent + oMLX = Caching-aware agent harness on macOS

    Claude Code’s source code leak revealed a huge gap in context management and cache-awareness comparing to its open-source alternatives like OpenCode.

    Hermes Agent is doing a better job at these among the “claws” ATM.

    hermes-agent.nousresearch.com

    mastodon.tevinzhang.com/@tevin

    #HermesAgent #oMLX #ClaudeCode #OpenCode

  7. Finally, an open-source alternative that's easy to use and performs better than #LMStudio on Mac with support for MLX!

    A bit shady that it uploads the benchmark result without noticing or asking tho

    omlx.ai

    #oMLX