mlx-dspark
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, ternary Bonsai-27B.
ARahim3/mlx-dspark
View on GitHub ↗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, ternary Bonsai-27B.
mlx-dspark grew +6.1% in the last 30 days, ranks 72nd of 303 in Inference Optimization, last commit 19 days ago.
Star trajectory
62 days tracked+6.1% in 30d, above the Inference Optimization median of +1.5%.
Last commit 19 days ago, staler than the median of 15d.
How it compares in Inference Optimization
Ranked 72nd of 303 by stars.
- Language
- Python
- License
- MIT License
- Contributors
- 4
- Forks
- 63
- Watchers
- 7
- Open issues
- 18
- Releases
- 58
- Created
- 2026-06-29
- Stars this week
- +6
You've seen where mlx-dspark stands today.
Get the moves before everyone else: the 5 Inference Optimization repos climbing fastest, every Tuesday.
Free weekly digest. Double opt-in, unsubscribe anytime.