JetBrains/Mellum2-12B-A2.5B-Instruct-GGUF-MXFP4_MOE

Quantization vs JetBrains/Mellum2-12B-A2.5B-Instruct. JetBrains/Mellum2-12B-A2.5B-Instruct-GGUF-MXFP4_MOE is a GGUF quantization (MXFP4/Q8_0) of the same weights: 141 tensors match exactly and 114 within quantization error.

Tensors changed: Embeddings 0/1, Norms 0/113, MLP 0/28, Attention 0/112, lm_head 0/1

On the Hub · Downloads on Model Pulse