[loudmax]

You can run the smaller Llama variants on consumer grade hardware, but people typically rent GPUs from the cloud to run the larger variants. It is possible to run even larger variants on a beefy workstation or gaming rig, but the performance on consumer hardware usually makes this impractical.

So the comparison would be the cost of renting a cloud GPU to run Llama vs querying ChatGPT.

[ramesh31]

>So the comparison would be the cost of renting a cloud GPU to run Llama vs querying ChatGPT.

Yes, and it doesn't even come close. Llama2-70b can run inference at 300+tokens/s on a single V100 instance at ~$0.50/hr. Anyone who can should be switching away from OpenAI right now.

[cheptsov]

How do you fit Llama2-70b into V100? V100 is 16GB. Llama2-70b 4bit would require up to 40GB. Also, what do you use for inference to get 300+tokens/s?

[thewataccount]

What's the best way to use LLama2-70b without existing infrastructure for orchestrating it?

[mjirv]

I stumbled upon OpenRouter[0] a few days ago. Easiest I’ve seen by far (if you want SaaS, not hosting it yourself).

[0] https://openrouter.ai

[ramesh31]

>What's the best way to use LLama2-70b without existing infrastructure for orchestrating it?

That's an exercise left to the reader for now, and is where your value/moat lies.

[thewataccount]

> That's an exercise left to the reader for now, and is where your value/moat lies.

Hopefully more on-demand services enter the space. Currently where I am we don't have the resources for any type of self orchestration and our use case is so low/sporadic that we can't simply have a dedicated instance.

Last I saw the current services were rather expensive but I should recheck.

[pdntspa]

I bought an old server off ServerMonkey for like $700 with a stupid amount of RAM and CPUs and it runs Llama2-70b fine, if a little slowly. Good for experimenting