google/gemma-4-E4B-it-qat-q4_0-unquantized
Full fine-tune vs google/gemma-4-E4B-it. Fine-tune: 94% of the weights changed, across 42 of 42 layers.
Tensors changed: MLP 126/606, Norms 212/484, other 126/261, Attention 132/719, Embeddings 3/6
39 derivatives checked
- google/gemma-4-E4B-it-qat-q4_0-gguf: Quantization (fewer layers)
- google/gemma-4-E4B-it-qat-w4a16-ct: Quantization
- unsloth/gemma-4-E4B-it-qat-GGUF: Not comparable yet
- huihui-ai/Huihui-gemma-4-E4B-it-qat-q4_0-unquantized-abliterated-GGUF: Abliterated (fewer layers)
- lmstudio-community/gemma-4-E4B-it-QAT-GGUF: Quantization (fewer layers)
- unsloth/gemma-4-E4B-it-qat-w4a16: Quantization
- mlx-community/gemma-4-e4b-it-qat-OptiQ-4bit: Quantization
- prithivMLmods/gemma-4-E4B-it-qat-GGUF: Same weights, converted (fewer layers)
- JMingo/gemma-4-E4B-it-qat-GGUF: Same weights, converted (fewer layers)
- mradermacher/gemma-4-E4B-it-qat-q4_0-unquantized-i1-GGUF: Quantization (fewer layers)
- cyankiwi/gemma-4-E4B-it-qat-AWQ-INT4: Quantization
- Zagol/gemma-4-E4B-it-qat-GGUF: Not comparable yet
- mradermacher/gemma-4-E4B-it-qat-q4_0-unquantized-GGUF: Same weights, converted (fewer layers)
- timfromhcs/Gemma-4-E4B-it-qat-q4_0-unquantized-abliterated-GGUF: Abliterated (fewer layers)
- xbill9/gemma-4-E4B-it-qat-q4_0-exact-gguf: Quantization (fewer layers)
- asincole/gemma-4-E4B-it-qat-q4_0-gguf: Quantization (fewer layers)
- nwtgck/gemma-4-E4B-it-qat-q4_0-gguf: Quantization (fewer layers)
- hung2903/gemma-4-E4B-vaccine-xai-merged-qat: Quantization (fewer layers)
- unsloth/gemma-4-E4B-it-qat-mobile: Quantization
- roman220220/gemma-4-E4B-it-qat-mlx: Quantization
- manojbillionaire123/gemma-4-E4B-it-qat-GGUF: Full fine-tune (fewer layers)
- TheStageAI/gemma-4-E4B-it-qat-GGUF: Quantization (fewer layers)
- tinybiggames/Huihui-gemma-4-E4B-it-qat-q4_0-unquantized-abliterated-GGUF: Abliterated (fewer layers)
- FreedomAISVR/Gemma-4-E4B-it-QAT-MXFP4-GGUF: Quantization (fewer layers)
- FreedomAISVR/Gemma-4-E4B-it-QAT-NVFP4-GGUF: Quantization (fewer layers)
- xbill9/gemma-4-E4B-it-qat-q4_0-w4a16-ct-text-ple4: Quantization
- alekshandru/gemma-4-E4B-it-qat-GGUF: Not comparable yet
- Grunzig/gemma-4-E4B-it-qat-oQ4e-fp16-mtp: Quantization
- NeveAI/Neve-Echo-S3-4B-QAT-GGUF: Quantization (fewer layers)
- RepublicOfKorokke/gemma-4-E4B-it-qat-q4_0-unquantized-oQ3e-text-fp16: Quantization
4 other repos hold byte-for-byte identical weight files.