nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16
Different architecture vs nvidia/NVIDIA-Nemotron-Nano-9B-v2. Different architecture: only 0 of 341/263 tensors match by name and shape.
39 derivatives checked
- lmstudio-community/NVIDIA-Nemotron-3-Nano-4B-GGUF: Quantization
- unsloth/NVIDIA-Nemotron-3-Nano-4B-GGUF: Same weights, converted
- unsloth/NVIDIA-Nemotron-3-Nano-4B: Identical copy
- HauhauCS/Nemotron3-Nano-4B-Uncensored-HauhauCS-Aggressive: Quantization
- bartowski/nvidia_Nemotron-3-Nano-4B-GGUF: Same weights, converted
- ggml-org/Nemotron-3-Nano-4B-GGUF: Same weights, converted
- mlx-community/NVIDIA-Nemotron-3-Nano-4B-4bit: Quantization
- VAREQON/NVIDIA-Nemotron-3-Nano-4B-BF16-i1-GGUF: Quantization
- mlx-community/NVIDIA-Nemotron-3-Nano-4B-OptiQ-4bit: Quantization
- roman220220/NVIDIA-Nemotron-3-Nano-4B-JANG-GPTQ-ipsupport-code-lora: Quantization
- mradermacher/NVIDIA-Nemotron-3-Nano-4B-BF16-GGUF: Same weights, converted
- mradermacher/NVIDIA-Nemotron-3-Nano-4B-BF16-i1-GGUF: Quantization
- tripolskypetr/Nemotron3-Nano-Uncensored-Aggressive-GGUF: Quantization
- build-small-hackathon/figment-finetuned-model-archive: Same weights, converted
- nazihara/Nemotron3-Nano-4B-Aggressive: Quantization
- budget-internalization-iclr2027/nemotron3-nano-4b-8k-grpo-hardyman-s300: Full fine-tune
- HauhauCS/Nemotron3-Nano-4B-Uncensored-HauhauCS-Aggressive-GenRM: Quantization
- budget-internalization-iclr2027/nemotron3-nano-4b-16k-grpo-firmbeetle-s120: Full fine-tune
- budget-internalization-iclr2027/nemotron3-nano-4b-4k-grpo-steadymagpie-s300: Full fine-tune
- Unrestricted/Nemotron3-Nano-4B-Uncensored-HauhauCS-Aggressive: Quantization
- unsloth/NVIDIA-Nemotron-3-Nano-4B-FP8: Quantization
- mlx-community/NVIDIA-Nemotron-3-Nano-4B-BF16: Same weights, repacked
- aleada/Nemotron-3-Nano-4B-W4A16: Quantization
- budget-internalization-iclr2027/nemotron3-nano-4b-2k-grpo-topdane-s300: Full fine-tune
- majentik/Nemotron-3-Nano-4B-TurboQuant-GGUF-Q4_K_M: Quantization
- budget-internalization-iclr2027/nemotron3-nano-4b-1k-grpo-usefulhippo-s300: Full fine-tune
- jaromer/Nemotron3-Nano-4B-Uncensored-HauhauCS-Aggressive: Quantization
- DevQuasar/nvidia.NVIDIA-Nemotron-3-Nano-4B-BF16-GGUF: Quantization
- majentik/Nemotron-3-Nano-4B-RotorQuant-GGUF-IQ4_XS: Quantization
- budget-internalization-iclr2027/nemotron3-nano-4b-2k-grpo-reasoninggym-coolbengal-s300: Full fine-tune
4 other repos hold byte-for-byte identical weight files.