Hacker News: GreyOctenhttps://news.ycombinator.com/user?id=GreyOctenHacker News RSShttps://hnrss.org/hnrss v2.1.1Tue, 30 Jun 2026 22:24:14 +0000<![CDATA[New comment by GreyOcten in "Show HN: A GPU/VRAM filter for finding LLMs that will run on your hardware"]]>handy, but the gap most of these filters have is that "fits in VRAM" doesn't mean usable. context length blows up the KV cache fast, a 7B that fits at 2k tokens will OOM at 32k. factoring context len + quant into the estimate is where it'd actually save people from getting burned.

]]>Fri, 26 Jun 2026 20:30:42 +0000https://news.ycombinator.com/item?id=48691596GreyOctenhttps://news.ycombinator.com/item?id=48691596https://news.ycombinator.com/item?id=48691596