google/gemma-4-12B-it-qat-q4_0-unquantized-assistant
Full fine-tune vs google/gemma-4-12B-it-assistant. Fine-tune: 100% of the weights changed, across 4 of 4 layers.
Tensors changed: Embeddings 1/1, Norms 17/21, other 5/6, MLP 12/12, Attention 8/8
11 derivatives checked
- Janvitos/gemma-4-12B-it-qat-assistant-MTP-Q8_0-GGUF: Quantization
- ji-farthing/gemma-4-qat-q4_0-MTP-assistants-ik-llama-GGUF: Quantization
- dahara1/gemma-4-12B-it-qat-assistant_gguf: Same weights, converted
- kunhunjon/gemma-4-12B-it-qat-assistant-w4a16-ct: Quantization
- mlx-community/gemma-4-12B-it-qat-assistant-4bit: Quantization
- RachidAR/gemma-4-12B-it-qat-q4_0-MTP-assistant-gguf: Quantization
- StoryArbor/gemma-4-mtp-drafters-GGUF: Quantization
- boxwrench/gemma-4-qat-mtp-assistant-heads: Full fine-tune
- Qwe1325/gemma-4-12B-it-qat-q4_0-unquantized-assistant-gguf: Same weights, converted
- ysong21/gemma-4-12B-it-qat-assistant-MTP-Q4_0-GGUF: Quantization
- ensky0/gemma-4-12B-it-qat-q4_0-gguf-assistant: Quantization
2 other repos hold byte-for-byte identical weight files.