| chankhavu/Nemotron-Cascade-2-30B-A3B-NVFP4 | nvidia/Nemotron-Cascade-2-30B-A3B | quantized | NVFP4 | 16.3B | L | other | chankhavu | 13 | 92.1k |
| bartowski/nvidia_Nemotron-Cascade-2-30B-A3B-GGUF | nvidia/Nemotron-Cascade-2-30B-A3B | quantized | GGUF | — | — | other | bartowski | 47 | 85.6k |
| stelterlab/Nemotron-Cascade-2-30B-A3B-AWQ | nvidia/Nemotron-Cascade-2-30B-A3B | quantized | AWQ | 5.05B | M | other | stelterlab | 4 | 41.1k |
| mradermacher/Nemotron-Cascade-2-30B-A3B-i1-GGUF | nvidia/Nemotron-Cascade-2-30B-A3B | quantized | GGUF | — | — | other | mradermacher | 25 | 34.2k |
| chankhavu/Nemotron-Cascade-2-30B-A3B-FP8 | nvidia/Nemotron-Cascade-2-30B-A3B | quantized | -FP8 | 31.6B | L | other | chankhavu | 1 | 26.8k |
| mradermacher/Nemotron-Cascade-2-30B-A3B-GGUF | nvidia/Nemotron-Cascade-2-30B-A3B | quantized | GGUF | — | — | other | mradermacher | 10 | 18.7k |
| mlx-community/Nemotron-Cascade-2-30B-A3B-4bit | nvidia/Nemotron-Cascade-2-30B-A3B | quantized | -4bit | 31.6B | L | other | mlx-community | 22 | 10.4k |
| empero-ai/openNemo-Cascade-2-30B-A3B | nvidia/Nemotron-Cascade-2-30B-A3B | finetune | — | 31.6B | L | other | empero-ai | 11 | 7.8k |
| cyankiwi/Nemotron-Cascade-2-30B-A3B-AWQ-4bit | nvidia/Nemotron-Cascade-2-30B-A3B | quantized | AWQ | 6.67B | M | other | cyankiwi | 2 | 6.1k |
| chankhavu/Nemotron-Cascade-2-30B-A3B-AWQ-INT4 | nvidia/Nemotron-Cascade-2-30B-A3B | quantized | AWQ | 5.05B | M | other | chankhavu | 5 | 5.7k |
| michaelw9999/Nemotron-Cascade-2-30B-A3B-NVFP4-GGUF | nvidia/Nemotron-Cascade-2-30B-A3B | quantized | NVFP4 | — | — | — | michaelw9999 | 6 | 4.8k |
| AesSedai/Nemotron-Cascade-2-30B-A3B-GGUF | nvidia/Nemotron-Cascade-2-30B-A3B | quantized | GGUF | — | — | — | AesSedai | 11 | 4.2k |
| mlx-community/Nemotron-Cascade-2-30B-A3B-8bit | nvidia/Nemotron-Cascade-2-30B-A3B | quantized | -8bit | 31.6B | L | other | mlx-community | 8 | 4.2k |
| chankhavu/Nemotron-Cascade2-30B-A3B-Eagle3-Long-Context | nvidia/Nemotron-Cascade-2-30B-A3B | finetune | — | 209M | S | apache-2.0 | chankhavu | 11 | 3.8k |
| mlx-community/Nemotron-Cascade-2-30B-A3B-6bit | nvidia/Nemotron-Cascade-2-30B-A3B | quantized | — | 31.6B | L | other | mlx-community | 5 | 4.1k |
| dealignai/Nemotron-Cascade-2-30B-A3B-UNCENSORED-JANG_2L | nvidia/Nemotron-Cascade-2-30B-A3B | finetune | — | 32.5B | L | other | dealignai | 5 | 3.8k |
| caiovicentino1/Nemotron-Cascade-2-30B-A3B-HLWQ-Q5 | nvidia/Nemotron-Cascade-2-30B-A3B | quantized | — | 20.3B | L | other | caiovicentino1 | 7 | 3.1k |
| noctrex/Nemotron-Cascade-2-30B-A3B-MXFP4_MOE-GGUF | nvidia/Nemotron-Cascade-2-30B-A3B | quantized | GGUF | — | — | — | noctrex | 5 | 2.9k |
| JANGQ-AI/Nemotron-Cascade-2-30B-A3B-JANG_2L | nvidia/Nemotron-Cascade-2-30B-A3B | finetune | — | 16.7B | L | other | JANGQ-AI | 3 | 2.7k |
| dealignai/Nemotron-Cascade-2-30B-A3B-JANG_2L-CRACK | nvidia/Nemotron-Cascade-2-30B-A3B | finetune | — | 36.2B | XL | other | dealignai | 9 | 2.4k |
| JANGQ-AI/Nemotron-Cascade-2-30B-A3B-JANG_4M | nvidia/Nemotron-Cascade-2-30B-A3B | finetune | — | 16.3B | L | other | JANGQ-AI | 5 | 2.5k |
| DevQuasar/nvidia.Nemotron-Cascade-2-30B-A3B-GGUF | nvidia/Nemotron-Cascade-2-30B-A3B | quantized | GGUF | — | — | — | DevQuasar | 0 | 1.9k |
| mlx-community/Nemotron-Cascade-2-30B-A3B-mlx-6bit | nvidia/Nemotron-Cascade-2-30B-A3B | quantized | mlx | 31.6B | L | other | mlx-community | 3 | 1.4k |
| RepublicOfKorokke/Nemotron-Cascade-2-30B-A3B-oQ3.5 | nvidia/Nemotron-Cascade-2-30B-A3B | quantized | — | 31.6B | L | other | RepublicOfKorokke | 1 | 1.1k |
| AdrienBrault/Nemotron-Cascade-2-30B-A3B-Q5_K_M-GGUF | nvidia/Nemotron-Cascade-2-30B-A3B | quantized | GGUF | — | — | other | AdrienBrault | 1 | 938 |
| RepublicOfKorokke/Nemotron-Cascade-2-30B-A3B-mlx-mxfp4 | nvidia/Nemotron-Cascade-2-30B-A3B | quantized | mlx | 31.6B | L | other | RepublicOfKorokke | 0 | 892 |
| mlx-community/Nemotron-Cascade-2-30B-A3B-mxfp4 | nvidia/Nemotron-Cascade-2-30B-A3B | quantized | mxfp4 | 31.6B | L | other | mlx-community | 1 | 839 |
| mlx-community/Nemotron-Cascade-2-30B-A3B-nvfp4 | nvidia/Nemotron-Cascade-2-30B-A3B | quantized | nvfp4 | 31.6B | L | other | mlx-community | 1 | 816 |
| mlx-community/Nemotron-Cascade-2-30B-A3B-mxfp8 | nvidia/Nemotron-Cascade-2-30B-A3B | quantized | — | 31.6B | L | other | mlx-community | 0 | 864 |
| shiny-plan/Nemotron-Cascade-2-30B-A3B-Q4_K_M-GGUF | nvidia/Nemotron-Cascade-2-30B-A3B | quantized | GGUF | — | — | other | shiny-plan | 1 | 796 |
| cyankiwi/Nemotron-Cascade-2-30B-A3B-AWQ-8bit | nvidia/Nemotron-Cascade-2-30B-A3B | quantized | AWQ | 10.4B | L | other | cyankiwi | 1 | 766 |
| mlx-community/Nemotron-Cascade-2-30B-A3B-5bit | nvidia/Nemotron-Cascade-2-30B-A3B | quantized | — | 31.6B | L | other | mlx-community | 1 | 690 |
| blascotobasco/Nemotron-Cascade-2-96E-A3B | nvidia/Nemotron-Cascade-2-30B-A3B | finetune | — | 24.2B | L | other | blascotobasco | 2 | 629 |
| curator-research/Llama-3.3-Nemotron-Cascade-2-30B-A3B-Curator-0.1.0-Enrichment-Thinking-OFF | nvidia/Nemotron-Cascade-2-30B-A3B | finetune | — | 31.6B | L | other | curator-research | 0 | 692 |
| curator-research/Llama-3.3-Nemotron-Cascade-2-30B-A3B-Curator-0.1.0-Enrichment-Thinking-ON | nvidia/Nemotron-Cascade-2-30B-A3B | finetune | — | 31.6B | L | other | curator-research | 0 | 691 |
| mlx-community/Nemotron-Cascade-2-30B-A3B-bf16 | nvidia/Nemotron-Cascade-2-30B-A3B | finetune | -bf16 | 31.6B | L | other | mlx-community | 0 | 678 |
| Ishowbackup/Nemotron-Cascade-2-30B-A3B-UNCENSORED-JANG_2L | nvidia/Nemotron-Cascade-2-30B-A3B | finetune | — | 32.5B | L | other | Ishowbackup | 0 | 621 |
| majentik/Nemotron-Cascade-2-30B-A3B-TurboQuant-GGUF-IQ4_XS | nvidia/Nemotron-Cascade-2-30B-A3B | quantized | GGUF | — | — | other | majentik | 1 | 555 |
| TitanPythons/Nemotron-Cascade-2-30B-A3B-UNCENSORED-JANG_2L | nvidia/Nemotron-Cascade-2-30B-A3B | finetune | — | 32.5B | L | other | TitanPythons | 0 | 540 |
| RepublicOfKorokke/Nemotron-Cascade-2-30B-A3B-mlx-nvfp4 | nvidia/Nemotron-Cascade-2-30B-A3B | quantized | mlx | 31.6B | L | other | RepublicOfKorokke | 0 | 510 |
| AdrienBrault/Nemotron-Cascade-2-30B-A3B-Q5_1-GGUF | nvidia/Nemotron-Cascade-2-30B-A3B | quantized | Q5_1 | — | — | other | AdrienBrault | 3 | 285 |
| shi3z/nemotron-cascade-2-attn-repeat-L5 | nvidia/Nemotron-Cascade-2-30B-A3B | quantized | — | 31.6B | L | other | shi3z | 2 | 299 |
| wyattearp/Nemotron-Cascade-2-30B-A3B-NVFP4 | nvidia/Nemotron-Cascade-2-30B-A3B | quantized | NVFP4 | 16.9B | L | other | wyattearp | 0 | 372 |
| majentik/Nemotron-Cascade-2-30B-A3B-TurboQuant-GGUF-Q4_K_M | nvidia/Nemotron-Cascade-2-30B-A3B | quantized | GGUF | — | — | other | majentik | 0 | 343 |
| majentik/Nemotron-Cascade-2-30B-A3B-RotorQuant-GGUF-Q8_0 | nvidia/Nemotron-Cascade-2-30B-A3B | quantized | GGUF | — | — | other | majentik | 0 | 341 |
| AdrienBrault/Nemotron-Cascade-2-30B-A3B-5bit-MLX | nvidia/Nemotron-Cascade-2-30B-A3B | quantized | MLX | 31.6B | L | other | AdrienBrault | 0 | 321 |
| majentik/Nemotron-Cascade-2-30B-A3B-TurboQuant-GGUF-Q3_K_M | nvidia/Nemotron-Cascade-2-30B-A3B | quantized | GGUF | — | — | other | majentik | 0 | 293 |
| TitanPythons/Nemotron-Cascade-2-30B-A3B-JANG_2L-CRACK | nvidia/Nemotron-Cascade-2-30B-A3B | finetune | — | 36.2B | XL | other | TitanPythons | 0 | 290 |
| audreyt/nemotron-cascade-2-attn-repeat-L5-GGUF | nvidia/Nemotron-Cascade-2-30B-A3B | quantized | GGUF | — | — | other | audreyt | 1 | 237 |
| majentik/Nemotron-Cascade-2-30B-A3B-TurboQuant-GGUF-Q5_K_M | nvidia/Nemotron-Cascade-2-30B-A3B | quantized | GGUF | — | — | other | majentik | 0 | 266 |
| majentik/Nemotron-Cascade-2-30B-A3B-TurboQuant-MLX-MXFP4 | nvidia/Nemotron-Cascade-2-30B-A3B | finetune | MLX | 4.94B | M | other | majentik | 0 | 158 |
| majentik/Nemotron-Cascade-2-30B-A3B-TurboQuant-MLX-8bit | nvidia/Nemotron-Cascade-2-30B-A3B | finetune | MLX | 8.89B | M | other | majentik | 0 | 105 |
| majentik/Nemotron-Cascade-2-30B-A3B-RotorQuant-MLX-3bit | nvidia/Nemotron-Cascade-2-30B-A3B | finetune | MLX | 3.95B | M | other | majentik | 0 | 94 |
| majentik/Nemotron-Cascade-2-30B-A3B-TurboQuant-MLX-4bit | nvidia/Nemotron-Cascade-2-30B-A3B | finetune | MLX | 4.94B | M | other | majentik | 0 | 94 |
| majentik/Nemotron-Cascade-2-30B-A3B-TurboQuant-MLX-6bit | nvidia/Nemotron-Cascade-2-30B-A3B | finetune | MLX | 6.91B | M | other | majentik | 0 | 91 |
| majentik/Nemotron-Cascade-2-30B-A3B-TurboQuant-MLX-5bit | nvidia/Nemotron-Cascade-2-30B-A3B | finetune | MLX | 5.93B | M | other | majentik | 0 | 88 |
| yavosh/go-nemotron-run01-adapter | nvidia/Nemotron-Cascade-2-30B-A3B | adapter | — | — | — | — | yavosh | 0 | 36 |
| dt-lindberg/asp-arc-agi-data | nvidia/Nemotron-Cascade-2-30B-A3B | adapter | — | — | — | — | dt-lindberg | 0 | 0 |
| SketchSSM/Nemotron-Cascade-2-30B-A3B-BF16 | nvidia/Nemotron-Cascade-2-30B-A3B | finetune | -BF16 | — | — | apache-2.0 | SketchSSM | 0 | 0 |