google/gemma-4-26B-A4B-it-qat-q4_0-unquantized
Full fine-tune vs google/gemma-4-26B-A4B-it. Fine-tune: 98% of the weights changed, across 30 of 30 layers.
Tensors changed: Embeddings 2/4, MLP 150/231, Norms 211/433, other 89/122, Attention 115/223
37 derivatives checked
- unsloth/gemma-4-26B-A4B-it-qat-GGUF: Not comparable yet
- google/gemma-4-26B-A4B-it-qat-q4_0-gguf: Quantization
- lmstudio-community/gemma-4-26B-A4B-it-QAT-GGUF: Quantization
- cyankiwi/gemma-4-26B-A4B-it-qat-AWQ-INT4: Quantization
- mlx-community/gemma-4-26B-A4B-it-qat-OptiQ-4bit: Quantization
- huihui-ai/Huihui-gemma-4-26B-A4B-it-qat-q4_0-unquantized-abliterated-GGUF: Abliterated
- reinforce20001/gemma4-26b-a4b-it-qat-w4a16-ct: Quantization
- prithivMLmods/gemma-4-26B-A4B-it-qat-GGUF: Same weights, converted
- adeepv/gemma-4-26B-A4B-it-W4A16-vLLM: Quantization
- mradermacher/gemma-4-26B-A4B-it-qat-q4_0-unquantized-i1-GGUF: Quantization
- Wiself/gemma-4-26B-A4B-QAT-Styletune-V2-Voice: Different architecture
- FreedomAISVR/Gemma-4-26B-A4B-it-QAT-NVFP4-GGUF: Quantization
- JMingo/gemma-4-26B-A4B-it-qat-GGUF: Same weights, converted
- Wiself/Dark-Scarlett-v1.0-QAT-26B-A4B-Voice: Full fine-tune
- mradermacher/gemma-4-26B-A4B-it-qat-q4_0-unquantized-GGUF: Quantization
- jcbtc/Gemma4-26B-CIRU-AMD-STRIX-vLLM: Quantization
- Wiself/Odette-26B-A4B-QAT-Voice: Full fine-tune
- Wiself/Boulesis-26B-A4B-QAT-Voice: Different architecture
- sakamakismile/Huihui-gemma-4-26B-A4B-it-qat-abliterated-MTP-NVFP4: Quantization
- mlx-community/gemma-4-26B-A4B-it-qat-q4_0-mlx-aligned: Quantization
- FreedomAISVR/Gemma-4-26B-A4B-it-QAT-MXFP4-GGUF: Quantization
- nwtgck/gemma-4-26B-A4B-it-qat-q4_0-gguf: Quantization
- kunhunjon/gemma-4-26B-A4B-it-qat-NVFP4-full: Quantization
- sakamakismile/Huihui-gemma-4-26B-A4B-it-qat-abliterated-pad768-NVFP4: Quantization
- xbill9/gemma-4-26B-A4B-it-qat-q4_0-w4a16-ct-text: Quantization
- Hagwell/gemma-4-26B-A4B-it-qat-GGUF: Not comparable yet
- ShaunGves/gemma-4-26B-A4B-it-qat-GGUF: Quantization
- prithivMLmods/gemma-4-26B-A4B-it-qat-ptq-NVFP4: Quantization
- OsaurusAI/gemma-4-26B-A4B-it-qat-MXFP4: Quantization
- RepublicOfKorokke/gemma-4-26B-A4B-it-qat-q4_0-unquantized-oQ3.5e-fp16: Quantization
4 other repos hold byte-for-byte identical weight files.