you are viewing a single comment's thread
view the rest of the comments
[–] 2 points 1 year ago* (2 children)

For those interested in the desktop-capable requirements: 16 GB GPU. 9070 XT?

For lighting fast performance with the OpenAI GPT-OSS 20B model, users can use the AMD Radeon™ 9070 XT 16GB graphics card in a desktop system.

Does it require that gen?

  • source
  • hideshow 2 child comments
  • [–] 2 points 1 year ago

    If your video card has 16+ Gb of memory you will be able to run it with: NVIDIA cards GTX 10 series or later on ollama.

    Ollama is easy, but it leaves a lot of performance on the table.

    If you have less than 16 GB, you may be able to get good performance using llama.cpp or especially Ik_llama.cpp.

  • source
  • parent
  • [–] 2 points 1 year ago

    Not sure it requires that gen, but it definitely needs the 16GB. I have a 6700 (XT?) with 12 GB and ollama loads up gpt-oss on my CPU. Whereas models like deepseek-r1 with 14b parameters runs solely on the GPU.

  • source
  • parent