Albond

DGX_Spark_Qwen3.5-122B-A10B-AR-INT4. Qwen3.5-122B-A10B on DGX Spark: 28.3 → 51 tok/s (+80%)

DGX_Spark_Unsloth_Lossless_Speedup. 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 validator, training, and merge.

WhisperCaption. 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 chat, movie-style subtitle strip, Apple Translation, searchable history.

UnivF2Law. Python

obfuscated-cjk-ocr. Two-stage occupancy + density OCR cascade for CJK characters from obfuscated web fonts. Python package, ~99.96% accuracy.