tensorblock/Qwen2-57B-A14B-Instruct-GGUF

Quantization vs Qwen/Qwen2-57B-A14B-Instruct. tensorblock/Qwen2-57B-A14B-Instruct-GGUF is a GGUF quantization (Q3_K_M) of the same weights: 169 tensors match exactly and 198 within quantization error.

Tensors changed: Embeddings 0/1, MLP 0/112, Attention 0/196, Norms 0/57, lm_head 0/1

On the Hub · Downloads on Model Pulse