No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by ARahim3 · Codex Skill · ★ 648
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is mlx-dspark safe to install? View the security audit →
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
| Stars | 648 |
| Forks | 53 |
| Language | Python |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 64.0292094748617/100 |
| Open Issues | 16 |
| Last Updated | 2026-09-10 |
| Created | 2026-06-29 |
| Platforms | claude-code, codex, python |
| Est. Tokens | ~25k |
These tools work well together with mlx-dspark for enhanced workflows:
Looking for a mlx-dspark alternative? If you're comparing mlx-dspark with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
The fastest way to run Qwen 3.8 Flash Next and Qwen 3.8 27B on a Mac: 125 tok/s in OpenCode on an M5 Max. Nati
High-performance OpenAI and Anthropic compatible LLM inference server for Apple Silicon. Native MLX, continuou
Native LLM inference server for Apple Silicon. OpenAI + Anthropic API compatible. No Python. Includes MLX Core
Synthetic Autonomic Mind - An AI assistant for everyone.
One Hub All LLMs For You | 为个人打造的 LLM API 聚合网关
Manage multiple Claude Code, OpenCode agents from either TUI or Web for easy access on mobile. Also supports M
Explore other popular codex skill tools:
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 648 GitHub stars.
mlx-dspark is primarily written in Python. It covers topics such as apple-silicon, claude-code, codex.
You can find installation instructions and usage details in the mlx-dspark GitHub repository at github.com/ARahim3/mlx-dspark. The project has 648 stars and 53 forks, indicating an active community.
mlx-dspark is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to mlx-dspark on Agent Skills Hub include MTPLX, vllm-mlx, mlx-serve. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: