redponike/Ling-Coder-lite-GGUF

Quantization vs inclusionAI/Ling-Coder-lite. redponike/Ling-Coder-lite-GGUF is a GGUF quantization (Q8_0) of the same weights: 85 tensors match exactly and 114 within quantization error.

Tensors changed: Attention 0/28, Norms 0/57, MLP 0/112, Embeddings 0/1, lm_head 0/1

On the Hub · Downloads on Model Pulse