HNHacker News
TopNewBestAskShowJobs

albinstman

146 karma · joined August 29, 2026

submissionscomments
albinstman··on Show HN: Llmspeed – feel how fast a local LLM runs before you buy the hardware
Would love to have multi-gpu support eventually but it's a balance between whats popular and what actually has good quality benchmarks available. Multi-gpu numbers can also vary between setups
albinstman··on Show HN: Llmspeed – feel how fast a local LLM runs before you buy the hardware
New model/hardware benchmarks is now live
albinstman··on Show HN: Llmspeed – feel how fast a local LLM runs before you buy the hardware
Qwen 3.8 flash next is already in the works and should be live soon.
albinstman··on Show HN: Llmspeed – feel how fast a local LLM runs before you buy the hardware
I’ll look into adding harnesses. The benchmark sources usually don’t contain harness so the problem is limited data. What models would you like to see?
albinstman··on Show HN: Llmspeed – feel how fast a local LLM runs before you buy the hardware
Thank you for the feedback. What model/quant did you test so I can look in it?
albinstman··on Launch HN: Almanac (YC S26) – AI that knows your company
Only nitpick maybe remove the red box next to the Pricing label on the pricing page. Looks like the Polish flag on first glance and I immediately thought “does it show me pricing from Poland”?
albinstman··on Launch HN: Almanac (YC S26) – AI that knows your company
Really simple and well designed website for the brand identity. Logo, background, UI and FAQ all flows well. Feel like I trust the project without knowing much about it or having the usual “trusted by” section. Keep it up!