mradermacher/Step-3.5-Flash-Ablitirated-GGUF

Quantization vs Kilinskiy/Step-3.5-Flash-Ablitirated. mradermacher/Step-3.5-Flash-Ablitirated-GGUF is a GGUF quantization (Q6_K) of the same weights: 223 tensors match exactly and 488 within quantization error.

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/181, MLP 0/261, Attention 0/225, other 0/42

On the Hub · Downloads on Model Pulse