• Irdial@lemmy.sdf.org
    link
    fedilink
    English
    arrow-up
    27
    ·
    2 days ago

    the Chinese AI lab also released a smaller, “distilled” version of its new R1, DeepSeek-R1-0528-Qwen3-8B, that DeepSeek claims beats comparably sized models on certain benchmarks

    Most models come in 1B, 7-8B, 12-14B, and 27+B parameter variants. According to the docs, they benchmarked the 8B model using an NVIDIA H20 (96 GB VRAM) and got between 144-1198 tokens/sec. Most consumer GPUs probably aren’t going to be able to keep up with

    • brucethemoose@lemmy.world
      link
      fedilink
      English
      arrow-up
      2
      ·
      edit-2
      2 days ago

      Depends on the quantization.

      7B is small enough to run it in FP8 or a Marlin quant with SGLang/VLLM/TensorRT, so you can probably get very close to the H20 on a 3090 or 4090 (or even a 3060) and you know a little Docker.

    • Avid Amoeba@lemmy.ca
      link
      fedilink
      English
      arrow-up
      7
      ·
      2 days ago

      It proved sqrt(2) irrational with 40tps on a 3090 here. The 32b R1 did it with 32tps but it thought a lot longer.

      • Irdial@lemmy.sdf.org
        link
        fedilink
        English
        arrow-up
        3
        arrow-down
        1
        ·
        edit-2
        2 days ago

        On my Mac mini running LM Studio, it managed 1702 tokens at 17.19 tok/sec and thought for 1 minute. If accurate, high-performance models were more able to run on consumer hardware, I would use my 3060 as a dedicated inference device