42ailab/DeepSeek-OCR-2-GGUF

Quantization vs deepseek-ai/DeepSeek-OCR-2. 42ailab/DeepSeek-OCR-2-GGUF is a GGUF quantization (Q4_K_M) of the same weights: 36 tensors match exactly and 86 within quantization error.

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/25, MLP 0/47, Attention 0/48

On the Hub · Downloads on Model Pulse