sugarforever/chat-ollama

Llama3.1:405b 对话 不工作

caih1943 opened this issue · 5 comments

Llama3.1:405b 对话 不工作 :
Ollama call failed with status code 500: llama runner process has terminated: error loading model: unable to allocate backend buffer

你通过 ollama 提供的终端命令能进行对话吗?

我刚试了一下,同样Error: llama runner process has terminated: error loading model: unable to allocate backend buffer

所以这与 chatollama 无关了。会不会是你的模型太大了,内存不够用?

32Gb RAM also faced this problem, unable to run it

32GB 内存带不动 405b 吧?