deepseek-ai/DeepSeek-V4-Flash-DSpark
5 derivatives checked
- alessandrobologna/DeepSeek-V4-Flash-DSpark-Drafter-GGUF: Not comparable yet
- lovesenko/DeepSeek-V4-Flash-DSpark-Abliterated: LoRA-style
- TensorFold/DeepSeek-V4-Flash-DSpark-MLX: Quantization
- yailabs/DeepSeek-V4-Flash-GGUF: Not comparable yet
- anemll/DeepSeek-V4-Flash-NVFP4-TP2-W4A4-v1: Quantization
2 other repos hold byte-for-byte identical weight files.