google/gemma-3-12b-it
Full fine-tune vs google/gemma-3-12b-pt. Fine-tune: 97% of the weights changed, across 48 of 48 layers.
Tensors changed: Embeddings 1/4, Norms 290/400, MLP 144/252, Attention 192/408, other 1/1
134 derivatives checked
- abhishekchohan/gemma-3-12b-it-quantized-W4A16: Quantization
- gaunernst/gemma-3-12b-it-int4-awq: Quantization
- MaziyarPanahi/gemma-3-12b-it-GGUF: Same weights, converted (fewer layers)
- unsloth/gemma-3-12b-it-GGUF: Same weights, converted (fewer layers)
- ISTA-DASLab/gemma-3-12b-it-GPTQ-4b-128g: Quantization
- lmstudio-community/gemma-3-12b-it-GGUF: Quantization (fewer layers)
- Lightricks/gemma-3-12b-it-qat-q4_0-unquantized: Full fine-tune
- bartowski/google_gemma-3-12b-it-GGUF: Same weights, converted (fewer layers)
- ggml-org/gemma-3-12b-it-GGUF: Same weights, converted (fewer layers)
- DreamFast/gemma-3-12b-it-heretic: Abliterated
- DreamFast/gemma-3-12b-it-heretic-v2: Abliterated
- google/gemma-3-12b-it-qat-q4_0-unquantized: Full fine-tune
- RedHatAI/gemma-3-12b-it-quantized.w4a16: Quantization
- unsloth/gemma-3-12b-it-bnb-4bit: Quantization
- unsloth/gemma-3-12b-it-unsloth-bnb-4bit: Quantization
- TheDrummer/Tiger-Gemma-12B-v3-GGUF: Quantization (fewer layers)
- mlabonne/gemma-3-12b-it-abliterated-GGUF: Abliterated (fewer layers)
- RedHatAI/gemma-3-12b-it-FP8-dynamic: Quantization
- mradermacher/gemma-3-12b-it-i1-GGUF: Quantization (fewer layers)
- DavidAU/Gemma-3-12b-it-MAX-HORROR-Imatrix-GGUF: Quantization (fewer layers)
- second-state/gemma-3-12b-it-GGUF: Same weights, converted (fewer layers)
- lmstudio-community/gemma-3-12B-it-qat-GGUF: Full fine-tune (fewer layers)
- eaddario/gemma-3-12b-it-GGUF: Same weights, converted (fewer layers)
- Andycurrent/gemma-3-12b-it-uncensored-GGUF: Abliterated (fewer layers)
- NbAiLab/borealis-open-12b: Full fine-tune
- Speech-AI-Research-Center/SARC-Taigi-LLM-12b-GGUF: Full fine-tune (fewer layers)
- tripolskypetr/gemma-3-12b-it: Same weights, converted (fewer layers)
- TheDrummer/Gemma-3-R1-12B-v1-GGUF: Quantization (fewer layers)
- saidutta69/gemma-3-12b-it-heretic: Abliterated
- nocturne23/gemma-3-12b-it-Q4_K_M-GGUF: Quantization (fewer layers)
31 other repos hold byte-for-byte identical weight files.