July pfp
July
@july
My usage this week: - 80% Deepseek v3 / R1, I'd say mainly R1 - 15% Claude Sonnet until I run out of tokens - leftovers go to ChatGPT - playing around on runpod / local model for random experimentation etc, LM studio, ollama, stable diffusion, etc I can't believe how much i'm using DS
16 replies
6 recasts
118 reactions

Dan Romero pfp
Dan Romero
@dwr.eth
How are you using R1? Web or local?
1 reply
4 recasts
20 reactions

July pfp
July
@july
Mainly web deployed to my own cluster
2 replies
0 recast
13 reactions

Brad Barrish pfp
Brad Barrish
@bradbarrish
Give me an idea of what you estimate the costs to be.
1 reply
0 recast
1 reaction

July pfp
July
@july
Running the full R1 671B fp16, sparse activated (9 x H200s on Lambda) is about ~$50/hr but prob things you can do to bring it down, or go slower toks/sec
1 reply
0 recast
4 reactions