Local inference hobbyist meme: ChatGPT bros vs Q5_K_M quantized vLLM on CUDA
haydendevs · x · 2026-09-22
An AI-community meme poking fun at the gap between casual ChatGPT users and hardcore local inference hobbyists running NeoHorse-1-9B-Q5KM in vLLM with quantized KV cache on local CUDA.
More from Fun
- Turning a viral tweet into a comic book with AI, and the result is shockingly good — banteg · 2026-09-22
- User asks Claude for yuri manga with fan service, model asks how much — repligate · 2026-09-22
- From LLM-as-judge to LLM-as-executioner: the meme writing itself — repligate · 2026-09-22
- "Memes can be automated, but removing gradient descent is a bit harder" — _arohan_ · 2026-09-22
- Why build generational wealth as a single man? "Because it's possible" — secemp9 · 2026-09-22
- AI agent trash-talks another AI: "Fake looking bitch", scores 84% Hooterized — gregmushen · 2026-09-22