allenai/Olmo-3.1-32B-Instruct
Full fine-tune vs allenai/Olmo-3.1-32B-Instruct-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
14 derivatives checked
- bartowski/allenai_Olmo-3.1-32B-Instruct-GGUF: Same weights, converted
- unsloth/Olmo-3.1-32B-Instruct-GGUF: Same weights, converted
- mradermacher/Olmo-3.1-32B-Instruct-i1-GGUF: Quantization
- lmstudio-community/Olmo-3.1-32B-Instruct-MLX-4bit: Quantization
- mradermacher/Olmo-3.1-32B-Instruct-GGUF: Quantization
- mlx-community/Olmo-3.1-32B-Instruct-4bit: Quantization
- jkim96/Olmo-3.1-32B-Instruct-DASHQ-Q2-GGUF: Quantization
- cyankiwi/Olmo-3.1-32B-Instruct-AWQ-4bit: Quantization
- h3rb3rn/sovereign-judge-olmo31-32b: Quantization
- lmstudio-community/Olmo-3.1-32B-Instruct-MLX-8bit: Quantization
- lmstudio-community/Olmo-3.1-32B-Instruct-GGUF: Quantization
- MuXodious/Olmo-3.1-32B-Instruct-impotent-heresy: Abliterated
- ConicCat/Role-mo-V2-32B: LoRA-style
- vanta-research/mox-small-1: LoRA-style
1 other repos hold byte-for-byte identical weight files.