Popular repositories Loading

1. DGX_Spark_Qwen3.5-122B-A10B-AR-INT4 DGX_Spark_Qwen3.5-122B-A10B-AR-INT4 Public

   Qwen3.5-122B-A10B on DGX Spark: 28.3 → 51 tok/s (+80%)

   Python 315 41

2. DenseSpark-Qwen3.8-27B DenseSpark-Qwen3.8-27B Public

   Optimized Qwen3.8-27B inference on NVIDIA DGX Spark

   Python 16 2

3. SingleSpark-Qwen3.8-Flash-Next SingleSpark-Qwen3.8-Flash-Next Public

   Experimental: Qwen3.8-Flash-Next (180B/6B MoE) on one NVIDIA DGX Spark at 44 tok/s — 4-bit NVFP4 + FP8 hybrid under vLLM, with the quality cost measured and published

   Python 13

4. DGX_Spark_Unsloth_Lossless_Speedup DGX_Spark_Unsloth_Lossless_Speedup Public

   7.67× LoRA / 8.35× Full FT speedup for Qwen3.5 (0.8B–27B) on NVIDIA DGX Spark — wall-clock parity with rented H100. Lossless within BF16. Three-command interactive wizard handles model picker, data…

   Python 12 1

5. WhisperCaption WhisperCaption Public

   macOS app that captions your microphone and your Mac's audio simultaneously — two independent transcribed streams in real time. On-device WhisperKit or cloud STT (Deepgram, ElevenLabs). Two-column …

   Swift 9 1

6. InverterScout InverterScout Public

   A secure, self-hosted LuxPower inverter monitor for trusted home networks.

   Python 2 1