google/gemma-4-31B-it
Full fine-tune vs google/gemma-4-31B. Fine-tune: 98% of the weights changed, across 60 of 60 layers.
Tensors changed: Embeddings 2/4, Norms 241/523, other 50/62, MLP 180/261, Attention 230/338
254 derivatives checked
- nvidia/Gemma-4-31B-IT-NVFP4: Quantization
- RedHatAI/gemma-4-31B-it-FP8-block: Quantization
- google/gemma-4-31B-it-qat-q4_0-unquantized: Full fine-tune
- wangzhang/gemma-4-31B-it-abliterated: LoRA-style
- unsloth/gemma-4-31B-it-GGUF: Not comparable yet
- LilaRest/gemma-4-31B-it-NVFP4-turbo: Quantization
- RedHatAI/gemma-4-31B-it-FP8-dynamic: Quantization
- paperscarecrow/Gemma-4-31B-it-abliterated: Same weights, converted (fewer layers)
- cyankiwi/gemma-4-31B-it-AWQ-4bit: Quantization
- lmstudio-community/gemma-4-31B-it-MLX-8bit: Quantization
- QuantTrio/gemma-4-31B-it-AWQ: Quantization
- lmstudio-community/gemma-4-31B-it-MLX-4bit: Quantization
- lmstudio-community/gemma-4-31B-it-MLX-6bit: Quantization
- lmstudio-community/gemma-4-31B-it-MLX-5bit: Quantization
- HauhauCS/Gemma4-31B-QAT-Uncensored-HauhauCS-Balanced-MTP: Full fine-tune (fewer layers)
- Intel/gemma-4-31B-it-int4-AutoRound: Quantization
- RedHatAI/gemma-4-31B-it-NVFP4: Quantization
- bartowski/google_gemma-4-31B-it-GGUF: Same weights, converted (fewer layers)
- slashreboot/athena-class-model-a: Quantization (fewer layers)
- lmstudio-community/gemma-4-31B-it-GGUF: Quantization (fewer layers)
- mlx-community/gemma-4-31b-it-4bit: Quantization
- ggml-org/gemma-4-31B-it-GGUF: Not comparable yet
- unsloth/gemma-4-31B-it-unsloth-bnb-4bit: Quantization
- unsloth/gemma-4-31B-it-NVFP4: Quantization
- unsloth/gemma-4-31B-it: Identical copy
- ebircak/gemma-4-31B-it-4bit-W4A16-AWQ: Quantization
- OS-Software/gemma-4-31B-it-qat-q4_0-uncensored-heretic-GGUF: Full fine-tune (fewer layers)
- AtomicChat/gemma-4-31B-it-GGUF: Quantization (fewer layers)
- tiny-random/gemma-4-dense: Different architecture
- LiconStudio/Gemma-4-31B-it-abliterated-GGUF: Abliterated (fewer layers)
165 other repos hold byte-for-byte identical weight files.