https://busyjay.com/tags/sglang/ Recent content in sglang on BusyJay Hugo -- gohugo.io en-us Mon, 26 Oct 2026 03:00:00 +0800 https://busyjay.com/post/sglang-qwen3.8-flash-next-fp4-local/ Mon, 26 Oct 2026 03:00:00 +0800 https://busyjay.com/post/sglang-qwen3.8-flash-next-fp4-local/ Recently, I spent some of my spare time deploying Qwen3.8-Flash-Next for local inference at home and working through a series of optimizations. Here are a few things I learned along the way. First, the hardware: GPUs: 5090 D 32 GiB + 4080 Super 16 GiB Motherboard: X870E GODLIKE RAM: 192 GiB The 5090 uses PCIe 5.0 x16, while the 4080 connects over USB4. The main Qwen3.8-Flash-Next model has 48 Transformer layers and 125 billion parameters.