phacker007··on Run Qwen 3.8 Flash Next (125B) on consumer hardware (RTX 4090) at 100T/sI think the problem is maybe being the cock.
phacker007··on Run Qwen 3.8 Flash Next (125B) on consumer hardware (RTX 4090) at 100T/sare you using MTP with concurrent requests? I think there could be an issue with KV cache I had with llama.cpp that randomly threw in characters from other thread's KV cache...
phacker007··on Show HN: How I topped the HuggingFace open LLM leaderboard on two gaming GPUsI'm so dumb
phacker007··on Are the Mysteries of Quantum Mechanics Beginning to Dissolve?I knew you were going to say that.
phacker007··on MCP Apps: Extending servers with interactive user interfacesCalling it... Vibe clicking