A 4090 running through the full stack of AI video calls: Qwen3.8-27B local deployment, conversation delay of 2 seconds
Qwen3.8-27B has just been open sourced. I spent one night deploying it to the local 4090. I changed the LLM brain of the self-developed open source framework VoxEMW from the DeepSeek API to this local 27B. The measured delay dropped from 2.4 seconds to 2.0 seconds.
Kimi K3 seems to be cooked for me, and honestly, Grok 4.6, Gemini 3.7, DeepSeek V4 are way better.
Built Football Frenzy, a playable mini soccer game demo, and saved the version (ID: db774d2). What's in the game: • 5-a-side match on a striped canvas pitch with full
I canceled cursor and claude code this month
→ freebuff does the same thing → gpt 5.6 luna and deepseek v4 flash for free → one command and it's installed what's weird is how long it takes to actually feel "free".
CLAUDE WATERMARKS + BEST HERMES MODELS: This Week's Big Questions Answered
Three questions everyone is asking right now. Here are the straight answers: Question 1: Do Claude's new watermarks mean my content gets flagged as AI? Here's the trap nobody mentions: Write an article
You have reached the end of the archive
All of deepseek