noctrex/Qwen3-Coder-Next-REAM-MXFP4_MOE-GGUF

Same weights, converted vs bknyaz/Qwen3-Coder-Next-REAM. Same weights stored in another dtype (BF16 → MXFP4/BF16), plus 252 new tensors.

Tensors changed: Embeddings 0/1, Norms 0/121, MLP 0/192, Attention 0/48, lm_head 0/1

On the Hub · Downloads on Model Pulse