gx10

Here are 4 public repositories matching this topic...

4-5x faster Qwen3.5 on ASUS GX10 / DGX Spark — Hybrid INT4+FP8 + MTP via one shell script

asus nvidia-gpu qwen3-5 gx10

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

quantization vllm llm-inference deepseek gb10 dgx-spark gx10 glm-5-3-flash

Verified Qwen3.8-27B-FP8 recipe for one NVIDIA GX10 with SGLang, native MTP, telemetry summaries, and curated benchmark receipts.

benchmark llm-inference qwen speculative-decoding sglang qwen3 dgx-spark gx10

Normal DeepSeek V4 Flash 0731 on one ASUS GX10: 21.32 to 46.39 served-wall tok/s with DSpark.

benchmark ds4 llm-inference speculative-decoding gb10 dgx-spark deepseek-v4 gx10

To associate your repository with the gx10 topic, visit your repo's landing page and select "manage topics."