allenai/Olmo-3.1-32B-Think
Full fine-tune vs allenai/Olmo-3-32B-Think-DPO. Fine-tune: 100% of the weights changed, across 64 of 64 layers.
Tensors changed: Embeddings 1/1, MLP 192/192, Norms 257/257, Attention 256/256, lm_head 1/1
15 derivatives checked
- bartowski/allenai_Olmo-3.1-32B-Think-GGUF: Same weights, converted
- unsloth/Olmo-3.1-32B-Think-GGUF: Same weights, converted
- mradermacher/Olmo-3.1-32B-Think-i1-GGUF: Quantization
- PS4Research/0VOz3fgU0qp4lVar: LoRA-style
- PS4Research/Hk6vAazgWreoKsXr: LoRA-style
- mradermacher/Olmo-3.1-32B-Think-GGUF: Quantization
- PS4Research/NfEJUrTPxT77xQ8f: LoRA-style
- jkim96/Olmo-3.1-32B-Think-DASHQ-Q2-GGUF: Quantization
- mlx-community/Olmo-3.1-32B-Think-4bit: Quantization
- PS4Research/4wvQl2UniBkYhlEJ: LoRA-style
- mlx-community/Olmo-3.1-32B-Think-8bit: Quantization
- cyankiwi/Olmo-3.1-32B-Think-AWQ-4bit: Quantization
- lmstudio-community/Olmo-3.1-32B-Think-MLX-4bit: Quantization
- DevQuasar/allenai.Olmo-3.1-32B-Think-GGUF: Same weights, converted
- lmstudio-community/Olmo-3.1-32B-Think-GGUF: Quantization
1 other repos hold byte-for-byte identical weight files.