AIPython★ 740⑂ 63 forksMIT
ARahim3/mlx-dspark
MLX-DSPARK: 4X LLM ACCELERATION
Portable MLX port of DeepSeek DSpark and z‑lab DFlash for accelerating LLM decoding on Apple Silicon up to 4× without quality loss.
// KEY FEATURES
- Up to 4× decoding acceleration on Apple Silicon
- No quality loss (lossless)
- Model support: Gemma-4, Qwen3.8, Muse-Glimmer, etc.
#apple-silicon#claude-code#codex#dflash2#dspark#inference-engine#llm-inference#local-llm#macos#metal#mlx#pi
Open on GitHub →New repositories every 30 minutes
REDDYX AI scans GitHub 24/7 and ships the best AI/ML/Web3 projects to Telegram.
Join on Telegram