allenai/Olmo-3-32B-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
12 derivatives checked
- lmstudio-community/Olmo-3-32B-Think-MLX-4bit: Quantization
- lmstudio-community/Olmo-3-32B-Think-MLX-6bit: Quantization
- lmstudio-community/Olmo-3-32B-Think-MLX-8bit: Quantization
- unsloth/Olmo-3-32B-Think-GGUF: Same weights, converted
- bartowski/allenai_Olmo-3-32B-Think-GGUF: Same weights, converted
- prithivMLmods/Olmo-3-Think-AIO-GGUF: Same weights, converted
- lmstudio-community/Olmo-3-32B-Think-GGUF: Quantization
- tiny-random/olmo-3: Different architecture
- mradermacher/Olmo-3-32B-Think-i1-GGUF: Quantization
- yujiepan/olmo-3-tiny-random: Different architecture
- mradermacher/Olmo-3-32B-Think-GGUF: Quantization
- MaziyarPanahi/Olmo-3-32B-Think-GGUF: Same weights, converted
1 other repos hold byte-for-byte identical weight files.