mlx-dspark

by ARahim3 · Codex Skill · ★ 736

About mlx-dspark

DeepSeek's DSpark and z-lab's DFlash speculative decoding — native on Apple Silicon via MLX. Lossless drafters (same output, just faster) for Gemma-4, Qwen3, LFM2.5, Muse-Glimmer, Ornith-1.0, Qwen3.6, Qwen3.8, Nemotron, and Bonsai targets — plus any matched DSpark / DFlash checkpoint. Run them at the CLI, from Python, serve an OpenAI-compatible API to LM Studio / any local tool, or drive Claude Code with a model on your own Mac. mlx-dspark runs two EAGLE-family speculative-decoding drafters natively on Apple Silicon: DeepSeek's DSpar

apple-siliconclaude-codecodexdflash2dsparkinference-enginellm-inferencelocal-llmmacosmetal

Quick Facts

Stars736
Forks63
LanguagePython
CategoryCodex Skill
LicenseMIT
Quality Score36.8/100
Open Issues20
Last Updated2026-11-08
Created2026-06-29
Platformsclaude-code, codex, python
Est. Tokens~1653k

Compatible Skills

These tools work well together with mlx-dspark for enhanced workflows:

  • claude-code-local — semantic(0.47)+complementary+rare_topics+same_lang+similar_pop+shared_platform (76%)
  • Rapid-MLX — semantic(0.47)+complementary+rare_topics+same_lang+similar_pop+shared_platform (71%)
  • vllm-mlx — semantic(0.46)+complementary+rare_topics+same_lang+similar_pop+shared_platform (70%)
  • mlx-serve — semantic(0.49)+complementary+rare_topics+similar_pop+shared_platform (61%)

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular Python Agent Tools

Frequently Asked Questions

What is mlx-dspark?

mlx-dspark is Up to 4× faster LLM decoding on Apple Silicon, lossless. Native MLX port of DeepSeek's DSpark & z-lab's DFlash speculative decoding — Gemma-4, Qwen3.8, Muse-Glimmer, Nemotron, LFM2.5, Ornith-1.0, tern. It is categorized as a Codex Skill with 736 GitHub stars.

What programming language is mlx-dspark written in?

mlx-dspark is primarily written in Python. It covers topics such as apple-silicon, claude-code, codex.

How do I install or use mlx-dspark?

You can find installation instructions and usage details in the mlx-dspark GitHub repository at github.com/ARahim3/mlx-dspark. The project has 736 stars and 63 forks, indicating an active community.

What license does mlx-dspark use?

mlx-dspark is released under the MIT license, making it free to use and modify according to the license terms.

View on GitHub → Browse Codex Skill tools