Skip to content
TheChatArchiveThe Chat Archive
Human-written demonstration (OpenAssistant volunteers)· OpenAssistant (human-written)Hugging Face OpenAssistant Conversations (oasst2)

What are good consumer graphics cards for running AI?

In OpenAssistant data, “assistant” turns were written by human volunteers as demonstrations. They are not model outputs.
  1. User

    What are good consumer graphics cards for running AI?

  2. Assistant

    When it comes to running AI on consumer graphics cards, the most important factor to consider is the amount of GPU memory available. Here are some good options:

    NVIDIA GeForce RTX 3080: This card is widely regarded as one of the best GPUs for AI workloads due to its high memory capacity (10GB-20GB) and powerful tensor cores.

    NVIDIA GeForce RTX 3070: This GPU is slightly less powerful than the RTX 3080, but still has a significant amount of memory (8GB-16GB) and is a more affordable option.

    NVIDIA GeForce GTX 1660 Ti: This GPU is a budget-friendly option that still has a good amount of memory (6GB) and can manage many AI workloads.

    AMD Radeon RX 6800: This GPU is a strong competitor to the NVIDIA options and has a high memory capacity (16GB).

    AMD Radeon RX 5700 XT: Another budget-friendly option, this GPU has a decent amount of memory (8GB) and can handle many AI workloads.

    It is worth noting that the specific GPU you choose will depend on the AI workload you are running and your budget. If you need a GPU with even more memory, there are also higher-end options.

Responses were produced in different, uncontrolled contexts (system prompts, settings, prior turns). This is not a benchmark.