Popular repositories Loading

1. spark-bench spark-bench Public

   Mixed-capability LLM benchmark for DGX Spark — 57 scenarios, 10 domains, partial-credit grading, trial statistics

   HTML 164 13

2. Qwen3.8-27B-oMLX-MTP-Mac Qwen3.8-27B-oMLX-MTP-Mac Public

   Qwen 3.8 27B at 48-65 tok/s on a Mac Studio M4 Max — measured oMLX native-MTP recipe, same-day A/B vs mlx-vlm+MTP sidecar, raw benchmark JSON included

   Python 64 4

3. Qwen3.8-27B-NVFP4-DFlash2-DGX-Spark Qwen3.8-27B-NVFP4-DFlash2-DGX-Spark Public

   Reproducible Qwen3.8-27B NVFP4 + DFlash2 recipe and qualification evidence for one NVIDIA DGX Spark

   Python 29 1

4. qwen38-flash-next-omlx-mac qwen38-flash-next-omlx-mac Public

   Verified Qwen3.8 Flash Next oMLX Lightning MTP deployment guide for Apple Silicon

   Python 13 1

5. glm53-flash-one-spark glm53-flash-one-spark Public

   Shell 12

6. DeepSeek-V4-Flash-0731-DSpark-2x-DGX-Spark DeepSeek-V4-Flash-0731-DSpark-2x-DGX-Spark Public

   Qualified vLLM TP2 + DSpark K7 recipe for official DeepSeek V4 Flash 0731 on two DGX Sparks

   Shell 9 1