nvidia/NVIDIA-Nemotron-Nano-9B-v2
Different architecture vs nvidia/NVIDIA-Nemotron-Nano-12B-v2. Different architecture: only 84 of 369/341 tensors match by name and shape.
23 derivatives checked
- nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16: Different architecture
- nvidia/NVIDIA-Nemotron-Nano-9B-v2-FP8: Quantization
- nvidia/NVIDIA-Nemotron-Nano-9B-v2-NVFP4: Quantization
- bartowski/nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF: Same weights, converted
- nvidia/NVIDIA-NemotronLabs-VoiceChat-11B: Full fine-tune (fewer layers)
- nvidia/NVIDIA-Nemotron-Nano-9B-v2-Japanese: Full fine-tune
- dominguesm/NVIDIA-Nemotron-Nano-9B-v2-GGUF: Same weights, converted
- eaddario/IQ2_NL-IQ3_NL-Test-Models: Same weights, converted
- mlx-community/NVIDIA-Nemotron-Nano-9B-v2-4bits: Quantization
- gaianet/NVIDIA-Nemotron-Nano-9B-v2-GGUF: Same weights, converted
- DevQuasar/nvidia.NVIDIA-Nemotron-Nano-9B-v2-GGUF: Same weights, converted
- cyankiwi/NVIDIA-Nemotron-Nano-9B-v2-AWQ-4bit: Quantization
- second-state/NVIDIA-Nemotron-Nano-9B-v2-GGUF: Same weights, converted
- tatsuyaaaaaaa/NVIDIA-Nemotron-Nano-9B-v2-gguf: Same weights, converted
- weathermanj/NVIDIA-Nemotron-Nano-9B-v2-gguf: Same weights, converted
- Joakimpalm-Zen/NVIDIA-Nemotron-Nano-9B-v2-Q8_0-GGUF: Quantization
- mlx-community/NVIDIA-Nemotron-Nano-9B-v2-6bit: Quantization
- MaziyarPanahi/NVIDIA-Nemotron-Nano-9B-v2-GGUF: Same weights, converted
- empero-ai/openNemo-9B: Identical copy
- Lauarvik/NVIDIA-Nemotron-Nano-9B-v2-GGUF: Same weights, converted
- impacte/NVIDIA-Nemotron-Nano-9B-v2-GGUF: Same weights, converted
- urufura/NVIDIA-Nemotron-Nano-9B-v2-Japanese: Full fine-tune
- Mitchins/Aronnax-N9Bv2-1.0: LoRA-style
5 other repos hold byte-for-byte identical weight files.