Live and recent posts from across the Fediverse tagged #deepseekr1, aggregated by home.social.
#deepseekr1
is there any way to obtain a useful and fast local llm for agentic coding on 8GB VRAM (RTX 3060 TI)?
I tried #gemma3 4b, #deepseekr1 7b, #phi4mini and #qwen3 4b using #Ollama with #Cline but got poor results
#localllm #agenticai