Forum

论坛
本地AI 1号网
多语言国际区 Internationa...
 
Notifications
Clear all

多语言国际区 International

多语言交流区，欢迎国际用户 International discussion.
RSS订阅
页 7 / 8

My GPU isn't being used and Ollama or llama.cpp is running on CPU. What should I check?

最近由 pandaadmin 发的贴, 7 天 前

帖子: 1
查看: 12


Is running an LLM locally really private? What should I watch out for?

最近由 pandaadmin 发的贴, 7 天 前

帖子: 1
查看: 10


How much VRAM do I need to run a 7B, 13B or 70B model locally?

最近由 pandaadmin 发的贴, 7 天 前

帖子: 1
查看: 9


What do Q4_K_M, Q5_K_S and Q8_0 mean in GGUF model names?

最近由 pandaadmin 发的贴, 7 天 前

帖子: 1
查看: 6


Ollama vs LM Studio vs llama.cpp vs vLLM: which one should I use?

最近由 pandaadmin 发的贴, 7 天 前

帖子: 1
查看: 8


I get "CUDA out of memory" when loading a model. How do I fix it?

最近由 pandaadmin 发的贴, 7 天 前

帖子: 1
查看: 8


My GGUF model fails to load in llama.cpp or Ollama. How do I troubleshoot?

最近由 pandaadmin 发的贴, 7 天 前

帖子: 1
查看: 8


Is a Mac with Apple Silicon good for running local LLMs? How much memory do I need?

最近由 pandaadmin 发的贴, 7 天 前

帖子: 1
查看: 8


Qwen, Llama, DeepSeek, Mistral or Gemma: how do I choose a model?

最近由 pandaadmin 发的贴, 7 天 前

帖子: 1
查看: 7


Is a bigger context window always better? Why does it use so much memory?

最近由 pandaadmin 发的贴, 7 天 前

帖子: 1
查看: 11


页 7 / 8
Share: