hugpadhugpad

abenzerps / Spark-X2.6-4B-MLX-4bit

Agents4.1B1.3K4Updated Oct 20, 2026
Hugging Face

Downloads

1.3K

Likes

4

Last updated

Oct 20, 2026

License

apache-2.0

MLX 4-bit quantization of XHToken/Spark-X2.6-4B, an on-device hybrid-attention language model (4B parameters) engineered for high-efficiency agent execution. Native context: 1,048,576 tokens (1M).

Tasks & library

  • text generation
  • mlx

Tags

  • mlx
  • spark2_5
  • spark-x2.6
  • long-context
  • 1m-context
  • agent

Technical specifications

Parameters4.1B
Librarymlx
LanguagesNot available
Base modelXHToken/Spark-X2.6-4B
Licenseapache-2.0