di-zhang-fdu/Supra-50M-Instruct-GGUF

Quantization vs SupraLabs/Supra-50M-Instruct. di-zhang-fdu/Supra-50M-Instruct-GGUF is a GGUF quantization (Q6_K/Q2_K) of the same weights: 25 tensors match exactly and 85 within quantization error.

Tensors changed: Embeddings 0/1, Norms 0/25, MLP 0/36, Attention 0/48

On the Hub · Downloads on Model Pulse