home.social

Search

733 results for “thb”

  1. New week, new update for the slides of my talk "Run LLMs Locally":

    Now including Gemma4 and Qwen3-Omni with Vision and Audio support and new slides describing Llama.cpp server parameters.

    codeberg.org/thbley/talks/raw/

    #ai #llm #llamacpp #stablediffusion #gptoss #qwen3 #glm #localai #gemma4

  2. New week, new update for the slides of my talk "Run LLMs Locally":

    Now including Gemma4 and Qwen3-Omni with Vision and Audio support and new slides describing Llama.cpp server parameters.

    codeberg.org/thbley/talks/raw/

    #ai #llm #llamacpp #stablediffusion #gptoss #qwen3 #glm #localai #gemma4

  3. New update for the slides of my talk "Run LLMs Locally": Bonsai-8B

    The latest version of Llama.cpp now supports Vulkan with 1-bit quantized models like Bonsai: 8B model having 1.1 GB in size, 2.5 GB in RAM.

    codeberg.org/thbley/talks/raw/

    #ai #llm #llamacpp #stablediffusion #gptoss #qwen3 #glm #localai

  4. New update for the slides of my talk "Run LLMs Locally": Bonsai-8B

    The latest version of Llama.cpp now supports Vulkan with 1-bit quantized models like Bonsai: 8B model having 1.1 GB in size, 2.5 GB in RAM.

    codeberg.org/thbley/talks/raw/

    #ai #llm #llamacpp #stablediffusion #gptoss #qwen3 #glm #localai

  5. New update for the slides of my talk "Run LLMs Locally": Bonsai-8B

    The latest version of Llama.cpp now supports Vulkan with 1-bit quantized models like Bonsai: 8B model having 1.1 GB in size, 2.5 GB in RAM.

    codeberg.org/thbley/talks/raw/

    #ai #llm #llamacpp #stablediffusion #gptoss #qwen3 #glm #localai

  6. New update for the slides of my talk "Run LLMs Locally": WebGPU

    Now models can run completely inside the browser using Transformers.js, Vulkan and WebGPU (slower than llama.cpp, but already usable).

    codeberg.org/thbley/talks/raw/

    #ai #llm #llamacpp #stablediffusion #gptoss #qwen3 #glm #localai #webgpu

    don't expect llm generated code to be correct ↓

  7. New update for the slides of my talk "Run LLMs Locally":

    Now including Reranking, Qwen 3.5 (slower than Qwen 3, but includes Vision) and loading models with Direct I/O.

    codeberg.org/thbley/talks/raw/

    #llm #llamacpp #ollama #stablediffusion #gptoss #qwen3 #glm #opencode #localai #mcp

  8. I updated the slides for my talk "Run LLMs Locally":

    Now including image generation with Qwen3 and content classification from the Qwen3Guard Technical Report paper.

    codeberg.org/thbley/talks/raw/

    #llm #llamacpp #ollama #stablediffusion #gptoss #qwen3 #glm #opencode #localai

  9. I updated the slides for my talk "Run LLMs Locally":

    Now including requirements, costs, setup, llama.cpp, stable-diffusion.cpp, embeddings, function calling, opencode, image recognition, speech recognition, image generation, prompt injection and popular models like GPT-OSS, Qwen3, Qwen3-vl, Z-Image and Whisper.

    codeberg.org/thbley/talks/raw/

    #llm #llamacpp #stablediffusion #gptoss #qwen3 #opencode #php #digitalsovereignty #localai

  10. @thbenkoe gibt es irgendwo die "Toot des Tages" von @blickamabend archiviert? @FlohEinstein hatte da ein paar Klassiker in der #erugf und #tootingbier Thun Zeit, oder @realaendu ?

  11. thb-media 🦋📸 ♂️ 🇩🇪 🇪🇺 🦣 (@thb-media.bsky.social)

    bsky.app/profile/did:plc:ek6ez

    > "Almost 3,000 #IPP prisoners still in jail, mainly for minor offenses, without knowing when or if they will ever be released." #Labor and #Starmer are doing nothing to change this! theguardian.com/uk-news/series The biggest justice scandal in the UK next to the postal office horizon scandal.

  12. @jerger

    Es gibt jetzt Alternativen und keine Entschuldigung mehr, wenn man nicht den #Xodus vollzieht. Stephen King wurde es nach 11 Jahren bei #X zu düster: sueden.social/@thb_media/11349
    #The_Guardian und der FC St. Pauli haben bei #X schon ihre Sachen gepackt. Schafft das der Reutlinger GEAonline noch vor den #Gruene /n in #Reutlingen?
    #Reutlingen #Fediverse #X #MSK #Musk #stephenking #theguardian #fcsp

  13. @thbevilacqua #WalterBecker & #DonaldFagen have been inducted into the 2024 Songwriter's Hall of Fame. Yeah, #SteellyDan songs repay & reward close attention.

  14. #Thailand Baht (#THB) strengthens as nervous investors are selling US dollars. Trading in gold is a factor. nationthailand.com/business/40

  15. Am Donnerstag startet die

    🎙️ Vortrags­reihe an der #THBingen

    #Klima­schutz & (Wirtschafts)politik in Zeiten der Krise

    Start ist am 19.10.2023, wo Prof. Dr. Oleg Panferov und Prof. Dr. Katharina Eckartz (Mitwirkende der #Bins4f) sprechen werden über Klimaschutz & (Wirtschafts)politik in Zeiten der Krisen.

    Am 09.11.2023 spricht Prof. Dr. Frieder Kunz über Wahrnehmung und Wirkung der akustischen Umgebung auf Menschen und über Ansätze, diese zu gestalten.

    Beginn 18:00h

    th-bingen.de/campus/veranstalt

  16. #Thailand Baht (#THB) fall precipitously against the USD, nearly reaching a level of 37 to the dollar. Pheu Thai party's signature economic stimulus plan, which will distribute 560 THB to citizens, is view by experts as the cause of this sharp decline. Bank of Thailand raises key interest rate in response to government borrowing to finance the plan investing.com/news/economic-in