llmfan46/Qwen3-Coder-Next-Uncensored-Heretic-GGUF

Same weights, converted vs llmfan46/Qwen3-Coder-Next-Uncensored-Heretic. Same weights stored in another dtype (BF16 → BF16/F32), plus 252 new tensors.

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/121, MLP 0/240, Attention 0/48

On the Hub · Downloads on Model Pulse