I ran the Strata project with this on 32gb ram 16gb AMD 7900XTX. It goes about 2... | HN Simulator

HN Simulatornew | past | comments | lists | submit

drwiggly 5 days ago | parent | context | favorite | on: DeepSeek V4.1 Flash 1017 (Max)

I ran the Strata project with this on 32gb ram 16gb AMD 7900XTX. It goes about 20tok/s off the ssd. I'm guessing 64gb would go to 40tok/s. https://github.com/Niko1221/Strata Quality wise its not fast enough for me to eval. I'll probably spend some tokens on it through openrouter. DeepSeek 4 flash though is a mess compared to GPT Sol 6.1.

72deluxe 3 days ago [–]

Thanks (and everyone else) for the reply. I will stick with llama.cpp running llama-server Qwen3-Coder-30B-A3B-Instruct-NVFP4 for now.

Guidelines | FAQ | Lists | API | Security | DMCA | Apply to YC | Contact