Jump to content

All Activity

This stream auto-updates

  1. Past hour
  2. s8s8cotop
    s8s8cotop joined the community
  3. Today
  4. Cyberdevs
    Sure thing man. No I just wanted to test and see how the app handles file attachment and attached several files and the error occurred, but it was able to analyze a single somewhat short text file without any errors. I have to say that the files I've attached were pretty large files so I guess that's what cause the error. Thanks, yeah I didn't expect much from that rig but since you've asked for a benchmark on Polaris/Vega GPUs though I share my experience. I will give it a try later and keep you posted.
  5. engeldlgado
    Hi, @Cyberdevs. Thanks for the feedback. Custom models folder: I will implement this in the next update. It is a good idea, as not everyone wants large models residing on their main drive. Attachments & Web UI: Acknowledged. File attachments and vision capabilities for compatible models are already planned for future updates, also for WebUI. Regarding the large file error: This might actually be an issue with the context window or response size limit, rather than the file size itself. Was the AI in the middle of generating a response when this error occurred? Also in settings theres is an option to increase the context size, if the problem was the response size, it will be implemented in the future update... Also you tested the experimental engine? maybe work better because it has a custom kernel for AMD. Regarding the system freeze on KabyLake/RX580: I will note it down, but keep in mind that hardware combination might simply hit its limits when benchmarking a 4B model like Qwen3.
  6. Cyberdevs started following [App] ToshLLM — local LLMs on Intel + AMD GPU (Metal, AMD‑patched llama.cpp, open source)
  7. Cyberdevs
    @engeldlgado Hi there, nice job and thanks for sharing your awesome project. I know it's a work in progress but I have some suggestions if you feel up to it. 1. It would be nice to be able to load the models from another folder other than ~/models 2. The web UI doesn't support file attachment, it would be nice to be able to attach files from the web UI too. Two issues I've faced so far is that when I attach large files for the AI to examine it gives me this error which i guess it states the file is too large to be processed, is there a way to fix it? and the second issue is on my KabyLake rig with the RX580 the system froze while running benchmark on the Qwen3-4B-Q4_K_M.gguf file.
  8. sunwin13bz1
    sunwin13bz1 joined the community
  9. f8betmeukk
    f8betmeukk changed their profile photo
  10. f8betmeukk
    f8betmeukk joined the community
  11. new88kunet1
    new88kunet1 joined the community
  12. xoso666vncom1
    xoso666vncom1 joined the community
  13. Ouo Haba
    Ouo Haba joined the community
  14. kgp
    Does it help if you download SuiteBench from here: https://limewire.com/d/85agk#0U2IFHltVg ? This version works flawlessly with my MacBook Pro M1.
  15. indexwpscom
    indexwpscom joined the community
  16. surenmunoo
    @MaLd0n I dont see Peak GPU Temps
  17. m88zocom3
    m88zocom3 joined the community
  18. op88accom
    op88accom joined the community
  19. XLR
    Can't find how to disable it... Doesn't matter how many config files i have - i want to make this ugly ass menu disappear forever and never appear again. How?
  20. Black Daimond
    Black Daimond joined the community
  21. engeldlgado
    Can you test the experimental engine too in settings? it has a improvements about speed, etc The multi-GPU support will be available for testing on the next release (cooking update atm)
  22. MacNB
    Understood. Thank you
  23. Alpha22 started following [App] ToshLLM — local LLMs on Intel + AMD GPU (Metal, AMD‑patched llama.cpp, open source)
  24. Alpha22
    RX6600XT graphics card
  25. engeldlgado
    Try to use the smallest one first to test, btw, what kind of system spec you have? Qwen 4B
  26. kaoskinkae
    Perfect in OLD2: AppleHDA.kext + Wifi Intel OCLP (OpenCore Legacy Patcher) 😄 deleted and modified with custom icons. KGP
  27. trangchu123bbinfo
    trangchu123bbinfo changed their profile photo
  28. XanthraX
    I don't know why, my both systems freeze (with repeatting beats on my speakers and no disk activity) even when I try to download the model recommended by the app.
  29. Dior Dash
    Dior Dash changed their profile photo
  30. Koffein71
    Nice tool. Here my benchmarks on RX 6800 and Ryzen 9800X3D
  31. Airlink Tours Niagara Fall
    Airlink Tours Niagara Fall changed their profile photo
  32. W3b0
    @nmano Are these patches compatible with Arrow Lake - Intel Core Ultra?
  33. officialshopfronts
    officialshopfronts changed their profile photo
  34. Max.1974
  35. The1Day
    The1Day changed their profile photo
  36. Yesterday
  37. BALDY_MAN
    a bit late to the update party. z690 hack. update went well. not patched sound. using bluetooth to creative stage 2 sound bar
  38. ahlam
    ahlam changed their profile photo
  39. deeveedee
    An update from the original OCLP Developers: macOS Golden Gate 27 and the Future of OpenCore Legacy Patcher · Issue #1183 · dortania/OpenCore-Legacy-Patcher
  40. deeveedee
    The RestrictEvents.kext javascriptcore branch is for older pre-AVX systems. GitHub - acidanthera/RestrictEvents at javascriptcore · GitHub
  41. HyperX7 started following Wi-Fi Patcher Pro
  42. MacNB
    What's the advantage of DhinakG's javascriptcore branch of RestrictEvents.kext ? Can you pls point to download ?
  43. sun6969win
    sun6969win changed their profile photo
  44. engeldlgado
    I've sent you a DM with a link to download the language file from the repo. No rush at all, take your time. Thanks a lot, this kind of help is exactly what the project needs.
  45. deeveedee
    🙌 Still amazes me that this 2010 hackbookpro can run the latest Sequoia. Posting this with Safari Version 26.5 (20624.2.5.18.3). Booting with OC 1.0.7 using DhinakG's javascriptcore branch of RestrictEvents.kext (with revpatch=jsc).
  46. deeveedee
    Smooth update to Sequoia 15.7.8 RC2. Status unchanged from my previous post about RC1.
  47. deeveedee
    I was pleasantly surprised to find that while the 65W EliteDesk 800 G5 Mini is intended for 9th Gen Intel CPUs, it also supports the 8th Generation i5-8600 CPU. I had a barebones G5 mini and an extra i5-8600 that needed a home. Together they make a perfect, low-cost hack for Tahoe. GeekBench 6 CPU About This Hack
  48. MaLd0n
    It's great to know it worked, and thank you for the feedback.
  49. sunwinvorg
    sunwinvorg changed their profile photo
  50. kgp
    Bravo, maestro! It works now flawlessly on Apple Silicon and macOS 27! You passed the Golden Gate
  1. Load more activity
×
×
  • Create New...