Post

Log inSign up

Post

i am jack’s autism on X: "@arduino @Qualcomm 16GB RAM? Going to be running 2-bit quantized teraslop Qwen hallucinating 24/7."

@tylerjharden
i am jack’s autism
@tylerjharden
16GB RAM? Going to be running 2-bit quantized teraslop Qwen hallucinating 24/7.
4:41 PM · Aug 25, 202651.9KViews
11

Log in or sign up for X

See what’s happening and join the conversation

Continue with phone
or
Log in with username or email

Relevant people

Avatar
i am jack’s autism@tylerjhardenFollow

Trending now

Terms·Privacy·Cookies·Accessibility·Ads Info·© 2026 X Corp.
  • @arduino
    Arduino
    @arduino
    Aug 25
    The wait is over! Meet Arduino VENTUNO Q, where AI takes action. 💬 Run local LLMs like Qwen 3, Gemma 4, and Qwen 3 VLM directly on the board 🧠 NPU + CPU + GPU +MCU: @Qualcomm Dragonwing IQ-8275 with up to 40 dense TOPS of AI performance and STM32H5 microcontroller for
    00:00
    179
  • @tylerjharden
    i am jack’s autism
    @tylerjharden
    16GB RAM? Going to be running 2-bit quantized teraslop Qwen hallucinating 24/7.
    4:41 PM · Aug 25, 202651.9KViews
    11
  • @guilledenll
    Guilleden
    @guilledenll
    Aug 25
    Qwen 9B quantized for serialized tasks perfectly capable
  • @bad_latency
    Bad Latency
    @bad_latency
    Aug 25
    There are sizable Mixture of Experts models can run comfortably on 16GB with the right settings and 4-bit. I'm doing so right now on a miniPC.
    3
  • @bentleypc
    BentleyPC
    @bentleypc
    Aug 26
    Give it time, but yes. It's too soon for this one.