Gajesh
@gajesh
engineer, chaos agent @eigenlabs, creator @darkbloomai.
perpetually curious optimist. entropic. open innovation; formerly: LZ, Telegram
加入 December 2016
2.9K 正在關注 51.2K 粉絲
We are now also making it really fast to run local models, starting with Qwen 3.8 Flash on CUDA (DGX Spark) and as always: MLX;
Let the optimizations begin!
