google/gemma-3-12b-pt
25 derivatives checked
- google/gemma-3-12b-it: Full fine-tune
- unsloth/gemma-3-12b-it: Full fine-tune
- mlx-community/gemma-3-12b-it-bf16: Full fine-tune
- tencent/KaLM-Embedding-Gemma3-12B-2511: LoRA-style (fewer layers)
- unsloth/gemma-3-12b-pt: Identical copy
- m8than/gemma-3-12b-it-lenientchatfix: Full fine-tune
- cjvt/GaMS3-12B-Instruct: Full fine-tune (fewer layers)
- mradermacher/gemma-3-12b-pt-i1-GGUF: Quantization (fewer layers)
- p-e-w/gemma-3-12b-it-heretic: Full fine-tune
- unsloth/gemma-3-12b-it-FP8-Dynamic: Quantization
- DevQuasar-10/google.gemma-3-12b-pt-GGUF: Same weights, converted (fewer layers)
- mradermacher/gemma-3-12b-pt-GGUF: Quantization (fewer layers)
- MBZUAI-Paris/Nile-Chat-12B: Full fine-tune (fewer layers)
- McGill-NLP/AfriqueGemma-12B: Full fine-tune
- cjvt/GaMS3-12B: Full fine-tune (fewer layers)
- RoseG/MiniMiP: Full fine-tune (fewer layers)
- unsloth/gemma-3-12b-pt-unsloth-bnb-4bit: Quantization
- lapa-llm/lapa-12b-pt: Full fine-tune
- unsloth/gemma-3-12b-pt-bnb-4bit: Quantization
- p-e-w/gemma-3-12b-it-heretic-v2: Full fine-tune
- VIDraft/Gemma-3-R1984-12B: Full fine-tune
- haic-hmgu/dermatology-captioning-12b: LoRA-style
- aifeifei798/DarkIdol-Aria-12B: Full fine-tune
- hell0ks/ja-ko-vn-12b-v2: LoRA-style (fewer layers)
- ToastyPigeon/Gemma-3-Confetti-12B: LoRA-style (fewer layers)
2 other repos hold byte-for-byte identical weight files.