llmfan46/gemma-4-31B-it-qat-q4_0-uncensored-heretic-NVFP4-GGUF

Same weights, converted vs llmfan46/gemma-4-31B-it-qat-q4_0-unquantized-uncensored-heretic. Same weights stored in another dtype (BF16 → T40/BF16), plus 471 new tensors.

Tensors changed: Embeddings 0/1, Norms 0/361

On the Hub · Downloads on Model Pulse