utter-project/EuroLLM-22B-Instruct-2512
Full fine-tune vs utter-project/EuroLLM-22B-2512. Fine-tune: 100% of the weights changed, across 54 of 54 layers.
Tensors changed: Embeddings 1/1, Norms 108/109, MLP 162/162, Attention 216/216, lm_head 1/1
11 derivatives checked
- bartowski/utter-project_EuroLLM-22B-Instruct-2512-GGUF: Same weights, converted
- Euraika/EuroLLM-22B-Instruct-GPTQ: Quantization
- mradermacher/EuroLLM-22B-Instruct-2512-GGUF: Quantization
- mradermacher/EuroLLM-22B-Instruct-2512-i1-GGUF: Quantization
- IntraFind/EuroLLM-22B-Instruct-2512-FP8-Dynamic: Quantization
- mlx-community/EuroLLM-22B-Instruct-2512-mlx-4bit: Quantization
- mlx-community/EuroLLM-22B-Instruct-2512-mlx-8bit: Quantization
- sixelasacul/EuroLLM-22B-it-GGUF: Quantization
- DevQuasar/utter-project.EuroLLM-22B-Instruct-2512-GGUF: Same weights, converted
- aifeifei798/EuroLLM-22B-Instruct-2512-FT: LoRA-style
- EuropeanParliament/EuroLLM-22B-EU-legislative: LoRA-style