News for hackers. Stuff that matters.
Re:Show HN: LLM Inference Calculator – Estimate VRAM, Latenc... by maestroquirk on Friday August 28, 2026 @10:50AM (#49479385)
Need one for vision models too tbh. Token/s doesn't really map easily
Re:Show HN: LLM Inference Calculator – Estimate VRAM, Latenc... by popopanda on Friday August 28, 2026 @12:12PM (#49480662)
Yeah, tokens/s varies a lot based on workload. However, I’ve calibrated the estimator against public benchmarks, so it stays within a 30% error margin!

I'll definitely explore how to estimate vision models next!

Re:Show HN: LLM Inference Calculator – Estimate VRAM, Latenc... by zuuna on Friday August 28, 2026 @03:10PM (#49483002)
How about the other way around? I'll tell you my hardware and you tell me the possible stats? I've been having some problems with bigger models, using MoE to make it work for longer/tedious work like nightly sweeps that don't really on speed.
Re:Show HN: LLM Inference Calculator – Estimate VRAM, Latenc... by brownbear7 on Saturday August 29, 2026 @08:40AM (#49489456)
Could you add cost estimates too? I usually care about the tradeoff between VRAM/throughput and roughly what the same workload would cost on different providers.