Sudo su (@sudoingX)10년 된 GTX 1080 8GB Pascal GPU에서 Qwen3 8B를 로컬로 18~20 tok/s 속도로 구동하고, Hermes Agent로 자율 실행까지 성공했다는 사례입니다. 구형 소비자용 GPU에서도 소형 LLM 에이전트 실험이 가능하다는 점을 보여줍니다.https://x.com/sudoingX/status/2059347168763523273#qwen3 #llm #localinference #gpu #agent
Related
🤖 Sometimes I use ChatGPT in my head.I love using ChatGPT whenever I have a question or something or I just want to talk...
🤖 Sometimes I use ChatGPT in my head.I love using ChatGPT whenever I have a question or something or I just want to talk, but sometimes my phone is dead and I don't want to get up ...
What if the OpenAI versus Hugging Face incident was reframed as Coca Cola versus Pepsi? There'd be more questions.https:...
What if the OpenAI versus Hugging Face incident was reframed as Coca Cola versus Pepsi? There'd be more questions.https://www.youtube.com/shorts/nn5MU0D9Mqo#AI #AISecurity #OpenAI ...
#Python Friday #341: Deep Agents in #LangGraph - #aihttps://pythonfriday.dev/2026/07/341-deep-agents-in-langgraph/
#Python Friday #341: Deep Agents in #LangGraph - #aihttps://pythonfriday.dev/2026/07/341-deep-agents-in-langgraph/