vibe coding, Local LLM 🤩 host: llama cpp model: gemma-4-E4B-it-qat-UD-Q4_K_XL.gguf --mtp-enabled output tokens: (tg = 42 t/s) GPU: Ryzen AI - iGPU https://www.amd.com/en/blogs/2024/accelerating-llama
Views
—
Views
—
Loading velocity curve…
—Views / houraverage velocity since it published
—Peak velocitythe hottest sustained views/hr it ever hit
—vs. their normalpace relative to this creator's own baseline
—Engagementlikes per view — real engagement is hard to fake
—Agehow early Slope caught this surge