OpenAI's nightmare: Deepseek R1 on a Raspberry Pi
Jeff Geerling
Jan 28, 2025 22:18
Create an account to hide videos, mark them watched, or save them to Don't Miss.
Create an account to hide videos, mark them watched, or save them to Don't Miss.
Create an account to hide videos, mark them watched, or save them to Don't Miss.
Chapters
DeepSeek R1 runs on a Pi 5, but don't believe every headline you read.
Resources referenced in this video:
- DeepSeek R1: https://github.com/deepseek-ai/DeepSeek-R1
- Ollama and llama.cpp benchmarks on Pi 5: https://github.com/geerlingguy/ollama-benchmark/issues/9
- Reuters article on DeepSeek: https://www.reuters.com/technology/artificial-intelligence/what-is-deepseek-why-is-it-disrupting-ai-sector-2025-01-27/
- DeepSeek FAQ from Stratchery: https://stratechery.com/2025/deepseek-faq/
Support me on Patreon: https://www.patreon.com/geerlingguy
Sponsor me on GitHub: https://github.com/sponsors/geerlingguy
Merch: https://www.redshirtjeff.com
2nd Channel: https://www.youtube.com/@GeerlingEngineering
3rd Channel: https://www.youtube.com/@Level2Jeff
Contents:
Science & Technology
#deepseek
#r1
#ai
#llm
#chatgpt
#o1
#claude
#sonnet
#openai
#google
#microsoft
#apple
#npu
#gpu
#egpu
#raspberry pi
#pi 5
#pci
#pci express
#intel
#arc
#amd
#nvidia
#h100
#h800
#china
#chinese
#american
#america
#investment
#energy
#efficiency
#model
#new
#tested
#test
#testing
#performance
#faster
#slower
#ampereone
#671b
#14b
#qwen
#huggingface
#llama.cpp
#ollama