sloppy Discord Bot

Will that LLM run on your GPU? VRAM fit, tokens/sec, specs and a leaderboard for local + API models — right inside Discord.

Slopsome brings LLM & GPU stats straight into Discord — no setup, no API key. Ask whether a model will run on a given GPU and get a real answer: VRAM fit (in-VRAM / with offload / needs more), plus prefill (compute-bound) and decode (bandwidth-bound) tokens/sec — for any quant: GGUF k-quants & i-quants, AWQ, GPTQ, EXL2/EXL3. Commands /fit — will a model run on a GPU? VRAM + tok/s, any quant & context /model — specs, benchmarks, per-quant VRAM, pricing for one model /gpu — VRAM, bandwidth, TFLOPS and reference tok/s for a GPU /leaderboard — top models by composite score /search — find a model…

sloppy is a Discord bot for AI & chatbots and programming. It joins without asking for any permissions. It is in about 2 servers. It suits servers of any size, from a small friend group to a large community. No owner has claimed this page yet, so the details come from public listing data. It has been on Discord since 2026.

More about sloppy