tensorblock/Ministral-8B-Instruct-2410-GGUF

Quantization vs mistralai/Ministral-8B-Instruct-2410. tensorblock/Ministral-8B-Instruct-2410-GGUF is a GGUF quantization (Q3_K_M) of the same weights: 73 tensors match exactly and 254 within quantization error.

Tensors changed: Embeddings 0/1, Norms 0/73, MLP 0/108, Attention 0/144, lm_head 0/1

On the Hub · Downloads on Model Pulse