And that's why you run models locally. Or if you want a remote chat model, use something stateless like AWS Bedrock custom model import to avoid having stored chats on the server.
Not many non-gamers have hardware capable of running such a model locally - never mind the skills.
For most people, bash is not a tool for interacting with the computer, it is how they express their frustration with the computer (sometimes leaving damaged keyboards).
I have DeepSeek-R1 1.5b running on a Raspberry Pi 5.
I have DS-R1 14b Q6 running on my old AM4 Ryzen with a AMD GPU, without issues.
My primary workstation is running 32B Q8 and without issues. And it's simple!
That's not the DeepSeek R1 model that they're offering via the API on these servers. That's a Qwen model that's been fine-tuned on output from the big R1 model.
DeepSeek-R1-Distill-Qwen-1.5B, DeepSeek-R1-Distill-Qwen-7B, DeepSeek-R1-Distill-Qwen-14B and DeepSeek-R1-Distill-Qwen-32B are derived from Qwen-2.5 series, which are originally licensed under Apache 2.0 License, and now finetuned with 800k samples curated with DeepSeek-R1.
DeepSeek-R1-Distill-Llama-8B is derived from Llama3.1-8B-Base and is originally licensed under llama3.1 license.
DeepSeek-R1-Distill-Llama-70B is derived from Llama3.3-70B-Instruct and is originally licensed under llama3.3 license.
