How do you use LLMs for private discussions?

Question

I sometimes have things to discuss with LLMs, which are more private than usual. I was thinking how to do it in a way that doesn't reveal my identity. 1. Use Tor to access the provider? 2. Create a random account? 3. Use some form of untraceable payment (which one?) 4. Scrub all information provided to the LLM from personally identifiable information? It seems like a lot of effort. So is running a local LLM, for which I don't even have the hardware. How do you do it?

blinded · Accepted Answer

I spin up a gpu instance in a cloud, run my model via vllm, connect to it via an ssh tunnel. done.

downbad_ · Answer

Can't you do it logged out?

hbcondo714 · Answer

Maybe try Ollama Cloud, Prompt or response data is never logged or trained on:https://ollama.com/pricing

Havoc · Answer

With a local one

7402 · Answer

With llama.cpp, Intel i9-13900KS CPU, 96 GB RAM, RTX 4070 running locally.

The models I'm using right now with that are:

  gpt-oss-120b-F16.gguf
  Qwen_Qwen3.5-27B-Q4_K_M.gguf
  Qwen3.6-35B-A3B-UD-Q5_K_XL.gguf
  gemma-4-31B-it-UD-Q6_K_XL.gguf

ahdgs · Answer

i've been using OpenAI's os PII-masking model, works decently and lightweight enough to run virtually anywhere https://huggingface.co/openai/privacy-filter

RobotCaleb · Answer

I don't

How do you use LLMs for private discussions?

I spin up a gpu instance in a cloud, run my model via vllm, connect to it via an ssh tunnel. done.

Can't you do it logged out?

Maybe try Ollama Cloud, Prompt or response data is never logged or trained on:
https://ollama.com/pricing

With a local one

With llama.cpp, Intel i9-13900KS CPU, 96 GB RAM, RTX 4070 running locally.
The models I'm using right now with that are:
`gpt-oss-120b-F16.gguf Qwen_Qwen3.5-27B-Q4_K_M.gguf Qwen3.6-35B-A3B-UD-Q5_K_XL.gguf gemma-4-31B-it-UD-Q6_K_XL.gguf`

i've been using OpenAI's os PII-masking model, works decently and lightweight enough to run virtually anywhere https://huggingface.co/openai/privacy-filter

I don't

How do you use LLMs for private discussions?

I spin up a gpu instance in a cloud, run my model via vllm, connect to it via an ssh tunnel. done.

Can't you do it logged out?

Maybe try Ollama Cloud, Prompt or response data is never logged or trained on:https://ollama.com/pricing

With a local one

With llama.cpp, Intel i9-13900KS CPU, 96 GB RAM, RTX 4070 running locally.The models I'm using right now with that are: gpt-oss-120b-F16.gguf Qwen_Qwen3.5-27B-Q4_K_M.gguf Qwen3.6-35B-A3B-UD-Q5_K_XL.gguf gemma-4-31B-it-UD-Q6_K_XL.gguf

i've been using OpenAI's os PII-masking model, works decently and lightweight enough to run virtually anywhere https://huggingface.co/openai/privacy-filter

I don't

Maybe try Ollama Cloud, Prompt or response data is never logged or trained on:
https://ollama.com/pricing

With llama.cpp, Intel i9-13900KS CPU, 96 GB RAM, RTX 4070 running locally.
The models I'm using right now with that are:
`gpt-oss-120b-F16.gguf Qwen_Qwen3.5-27B-Q4_K_M.gguf Qwen3.6-35B-A3B-UD-Q5_K_XL.gguf gemma-4-31B-it-UD-Q6_K_XL.gguf`