nvidia/Nemotron-Orchestrator-8B
Partial fine-tune vs Qwen/Qwen3-8B. Partial change: 85% of the weights changed (attention, mlp, norms), in 36 of 36 layers.
Tensors changed: Embeddings 0/1, Norms 100/145, MLP 108/108, Attention 144/144, lm_head 0/1
7 derivatives checked
- MaziyarPanahi/Nemotron-Orchestrator-8B-GGUF: Same weights, converted
- bartowski/nvidia_Orchestrator-8B-GGUF: Same weights, converted
- mradermacher/Orchestrator-8B-i1-GGUF: Quantization
- mradermacher/Orchestrator-8B-GGUF: Same weights, converted
- DevQuasar/nvidia.Orchestrator-8B-GGUF: Quantization
- TeichAI/Nemotron-Orchestrator-8B-DeepSeek-v3.2-Speciale-Distill: LoRA-style
- sainikhiljuluri2015/NVIDIA-Orchestrator-Cybersecurity-8B-Merged: LoRA-style
2 other repos hold byte-for-byte identical weight files.