yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1-GGUF
Full fine-tune vs google/gemma-4-12B-it. yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1-GGUF is a GGUF (Q8_0) of different weights. Fine-tune: 100% of the weights changed, across 48 of 48 layers.
Tensors changed: Embeddings 1/1, Norms 260/289, MLP 144/144, Attention 184/184
6 derivatives checked
- Abiray/gemma-4-12B-coder-fable5-composer2.5-v1-GGUF: Same weights, repacked
- srv-sngh/gemma-4-12B-coder-fable5-composer2.5-nvfp4: Quantization
- sakamakismile/gemma-4-12B-coder-fable5-composer2.5-GGUF: Quantization
- sakamakismile/gemma-4-12B-coder-fable5-composer2.5-MTP-NVFP4: Quantization
- llmfan46/gemma-4-12B-coder-fable5-composer2.5-v1-uncensored-heretic: Quantization
- bingleai/gemma-4-12B-coder-fable5-composer2.5-v1-bf16: Full fine-tune