NVIDIA · 9B · Dense
Hybrid Mamba2 architecture for reasoning
291.6K downloads
508 likes
2025-06 128K context
Use Cases
reasoning
| Quant | Bits | VRAM | Quality | Status |
|---|---|---|---|---|
| Q2_K | 2 | 3.4 GB | low | — |
| Q3_K_M | 3 | 4.5 GB | moderate | — |
| Q4_K_M | 4 | 5.1 GB | good | — |
| Q5_K_M | 5 | 6.3 GB | good | — |
| Q6_K | 6 | 7.4 GB | excellent | — |
| Q8_0 | 8 | 9.7 GB | excellent | — |
| F16 | 16 | 18.9 GB | lossless | — |
GPUs that run Nemotron Nano 9B v2
Nemotron Nano 9B v2 needs about 5.1 GB of VRAM at Q4_K_M, so it runs comfortably on a GPU with 6 GB of VRAM or more (157 of the GPUs we track). Common cards, smallest first:
| VRAM | GPUs |
|---|---|
| 6 GB | RTX 2060 , Arc A380 , RX 5600 XT |
| 8 GB | RTX 5060 Ti , RX 7600 , Arc A750 |
| 10 GB | RTX 3080 , RX 6700M |
| 11 GB | RTX 2080 Ti , GTX 1080 Ti |
About this model
Hybrid Mamba2 architecture for reasoning