Crazy prefill speed of DwarfStar running DeepSeek v4 PRO in the DGX Station (private branch for now)…
Crazy prefill speed of DwarfStar running DeepSeek v4 PRO in the DGX Station (private branch for now) using techniques that leverage the peculiar RAM + VRAM mixed setup of the Station. 3000 t/s but even more can be reached.
Gemini 3.7 Flash
Grok 4.6 DeepSeek V4 Pro 0813 Sonnet 5 Gemini is better than you think?
I bet you $100 you haven't tried DeepSeek Harness yet 🚨
159,000 GitHub stars in five days MIT + runs local in a browser tab + reads the Claude Code settings file you already have ask it for a tool it doesn't have > it writes the plugin > mounts it mid session > keeps working
Which AI model actually wins?
DeepSeek V4 Flash vs Gemini 3.7 Flash vs Sonnet 5 vs GLM 5.2. • Same algorithm. Same challenge. Four different models. • Watch them go head to head in this AI Algorithm War and see who writes the best solution. • Who are you betting on?
You have reached the end of the archive
All of deepseek