nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
62 derivatives checked
- nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4: Quantization
- nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8: Quantization
- lmstudio-community/NVIDIA-Nemotron-3-Nano-30B-A3B-MLX-4bit: Quantization
- lmstudio-community/NVIDIA-Nemotron-3-Nano-30B-A3B-MLX-8bit: Quantization
- lmstudio-community/NVIDIA-Nemotron-3-Nano-30B-A3B-MLX-6bit: Quantization
- lmstudio-community/NVIDIA-Nemotron-3-Nano-30B-A3B-MLX-5bit: Quantization
- pipecat-ai/phonellm-alpha-1: Full fine-tune
- unsloth/Nemotron-3-Nano-30B-A3B-GGUF: Same weights, converted
- RedHatAI/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8: Quantization
- MultiverseComputingCAI/Pulsar-16B-BF16: Different architecture
- lmstudio-community/NVIDIA-Nemotron-3-Nano-30B-A3B-GGUF: Same weights, converted
- ggml-org/NVIDIA-Nemotron-3-Nano-30B-A3B-GGUF: Same weights, converted
- bartowski/nvidia_Nemotron-3-Nano-30B-A3B-GGUF: Same weights, converted
- stelterlab/NVIDIA-Nemotron-3-Nano-30B-A3B-AWQ: Quantization
- mudler/Nemotron-3-Nano-30B-A3B-APEX-GGUF: Quantization
- mradermacher/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16-i1-GGUF: Quantization
- HebArabNlpProject/Hebatron: Full fine-tune
- DhruvalLabs/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16-GGUF: Quantization
- unsloth/Nemotron-3-Nano-30B-A3B: Identical copy
- nvidia/NVIDIA-Nemotron-Labs-3-Elastic-30B-A3B-BF16: Full fine-tune
- mlx-community/NVIDIA-Nemotron-3-Nano-30B-A3B-MLX-6Bit: Quantization
- mradermacher/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16-GGUF: Quantization
- mlx-community/NVIDIA-Nemotron-3-Nano-30B-A3B-4bit: Quantization
- Ex0bit/Elbaz-NVIDIA-Nemotron-3-Nano-30B-A3B-PRISM: Same weights, converted
- pirola/Nemotron-3-Nano-30B-A3B-pirola-IQ3_XXS-GGUF: Not comparable yet
- nvidia/NVIDIA-Nemotron-Labs-3-Elastic-30B-A3B-NVFP4: Quantization
- minjaechoi/nemotron3-nano-30b-a3b-2p36bit-r16: LoRA-style
- mlx-community/NVIDIA-Nemotron-3-Nano-30B-A3B-OptiQ-4bit: Quantization
- mlx-community/NVIDIA-Nemotron-3-Nano-30B-A3B-MLX-8Bit: Quantization
- DemomanCA/NVIDIA-Nemotron-Labs-3-Elastic-30B-A3B-NVFP4-GGUF: Quantization
9 other repos hold byte-for-byte identical weight files.