Basic information
Model repository: inferencerlabs/DeepSeek-V4-Flash-MLX-Q2i
Organization: inferencerlabs
Tasks: text-generation
Architecture and runtime
Model type: deepseek_v4
Architecture: DeepseekV4ForCausalLM
Libraries: mlx, safetensors, pytorch
Base models: deepseek-ai/DeepSeek-V4-Flash
Current revision: master
License and update history
License: Not provided
Created: 2026-09-02
Last updated: 2026-09-02
Hardware requirements
Not filled in locally.
Download links
Not filled in locally.
Basic usage example
Not filled in locally.