google/gemma-2-9b-it
Full fine-tune vs google/gemma-2-9b. Fine-tune: 100% of the weights changed, across 42 of 42 layers.
Tensors changed: Embeddings 1/1, Norms 169/169, MLP 126/126, Attention 168/168
117 derivatives checked
- bartowski/gemma-2-9b-it-GGUF: Quantization
- unsloth/gemma-2-9b-it-bnb-4bit: Quantization
- lmstudio-community/gemma-2-9b-it-GGUF: Quantization
- hugging-quants/gemma-2-9b-it-AWQ-INT4: Quantization
- legraphista/gemma-2-9b-it-IMat-GGUF: Same weights, converted
- DiTy/gemma-2-9b-it-russian-function-calling-GGUF: LoRA-style
- mradermacher/gemma-2-9b-it-i1-GGUF: Quantization
- adamkarvonen/checkpoints_latentqa_cls_past_lens_addition_gemma-2-9b-it: Adapter
- QuantFactory/gemma-2-9b-it-DPO-GGUF: Full fine-tune
- QuantFactory/gemma-2-9b-it-WPO-HB-GGUF: Full fine-tune
- QuantFactory/gemma-2-9b-it-GGUF: Quantization
- RedHatAI/gemma-2-9b-it-FP8: Quantization
- QuantFactory/gemma-2-9b-it-SimPO-GGUF: Quantization
- qwp4w3hyb/gemma-2-9b-it-iMat-GGUF: Same weights, converted
- shenzhi-wang/Gemma-2-9B-Chinese-Chat: Full fine-tune
- moebiusT7/gemma-4-12b-mobius-custom: Quantization
- QuantFactory/gemma-2-9b-it-SimPO-GGUF-v2: Quantization
- QuantFactory/gemma-advanced-v1-GGUF: Full fine-tune
- SanctumAI/gemma-2-9b-it-GGUF: Same weights, converted
- QuantFactory/Atlas-Chat-9B-GGUF: Full fine-tune
- matrixportalx/gemma-2-9b-it-GGUF: Same weights, converted
- QuantFactory/WoonaV1.2-9b-GGUF: Full fine-tune
- DiTy/gemma-2-9b-it-function-calling-GGUF: LoRA-style
- OpenLLM-Ro/RoGemma2-9b-Instruct: Full fine-tune
- backyardai/gemma-2-9b-it-GGUF: Quantization
- QuantFactory/Quill-v1-GGUF: Quantization
- EasierAI/Gemma-2-9B: Quantization
- second-state/gemma-2-9b-it-GGUF: Same weights, converted
- mradermacher/gemma-2-9b-it-GGUF: Same weights, converted
- MBZUAI-Paris/Atlas-Chat-9B: LoRA-style
30 other repos hold byte-for-byte identical weight files.