phuongncn /asus-gx10-qwen35-speed-hack
4-5x faster Qwen3.5 on ASUS GX10 / DGX Spark — Hybrid INT4+FP8 + MTP via one shell script
Shell32

gx10 话题在 GitHub 上没有填写简介,这里按 Star 数汇总最相关的热门仓库。
4-5x faster Qwen3.5 on ASUS GX10 / DGX Spark — Hybrid INT4+FP8 + MTP via one shell script
Run DeepSeek-V4-Flash-0731, GLM-5.3-Flash on a single NVIDIA GB10 / DGX Spark - 2-bit MoE planes, FP4 quality recovery, speculative decoding
Verified Qwen3.8-27B-FP8 recipe for one NVIDIA GX10 with SGLang, native MTP, telemetry summaries, and curated benchmark receipts.
Normal DeepSeek V4 Flash 0731 on one ASUS GX10: 21.32 to 46.39 served-wall tok/s with DSpark.