Slopsome is a community for people who run large language models on their own hardware.
- 🖥️ Share your rig and the speeds you actually get
- 🧩 Talk quants (GGUF, AWQ, GPTQ, EXL2/EXL3), VRAM fit and tokens/sec
- ❓ “What can I run?” — bring your GPU, get honest answers
- 📊 Backed by slopsome.com — a free, no-login search engine for LLM & GPU stats, with a bot you can query right here
Whether you’re on a single 3060 or a multi-GPU rig, come compare notes. No cloud required.