NVIDIA-Nemotron-3-Super-120B-A12B-BF16 (NVIDIA) is a 120.0B parameters MoE (12.0B active per token) open-weight model tracked on AI Hashrate. At 8K context we estimate roughly 69.4 GB VRAM for Q4 (weights 66.0 GB + KV 2.4 GB + 1 GB overhead) and 243.4 GB for FP16. About 10 GPUs/accelerators in our catalog fully fit this model at Q4 under that context assumption. Fastest Q4 configs: B200 192GB SXM ≈ 424.2 tok/s (estimated); MI300X 192GB ≈ 281.1 tok/s (estimated); H200 141GB SXM5 ≈ 254.5 tok/s (estimated); H100 80GB SXM5 ≈ 177.7 tok/s (estimated); Gaudi 3 128GB ≈ 173.7 tok/s (estimated). Use the table below for VRAM fit and tok/s per dollar (list MSRP). Estimates follow memory-bandwidth math; measured rows override when present. See methodology for details. Methodology.
| Hardware | VRAM | Quant | tok/s | Fits? | tok/s/$ |
|---|---|---|---|---|---|
| B200 192GB SXM | 192 | Q4 | 424.2 est. | Yes | 0.011 |
| MI300X 192GB | 192 | Q4 | 281.1 est. | Yes | 0.019 |
| H200 141GB SXM5 | 141 | Q4 | 254.5 est. | Yes | 0.007 |
| B200 192GB SXM | 192 | FP16 | 207.4 est. | No | 0.005 |
| H100 80GB SXM5 | 80 | Q4 | 177.7 est. | Yes | 0.006 |
| Gaudi 3 128GB | 128 | Q4 | 173.7 est. | Yes | 0.014 |
| MI300X 192GB | 192 | FP16 | 137.4 est. | No | 0.009 |
| A100 80GB SXM4 | 80 | Q4 | 108.1 est. | Yes | 0.007 |
| RTX 6000 Ada 48GB | 48 | Q4 | 69.6 est. | No | 0.01 |
| H200 141GB SXM5 | 141 | FP16 | 67.1 est. | No | 0.002 |
| L40S 48GB | 48 | Q4 | 62.6 est. | No | 0.008 |
| RTX 5090 32GB | 32 | Q4 | 57.7 est. | No | 0.029 |
| RTX A6000 48GB | 48 | Q4 | 55.7 est. | No | 0.012 |
| Mac Studio M3 Ultra 96GB | 96 | Q4 | 43.4 est. | Yes | 0.011 |
| Mac Studio M2 Ultra 192GB | 192 | Q4 | 42.4 est. | Yes | 0.006 |
| Gaudi 3 128GB | 128 | FP16 | 37.7 est. | No | 0.003 |
| Mac mini M4 Pro 64GB | 64 | Q4 | 35.2 est. | No | 0.016 |
| MacBook Pro M4 Max 128GB | 128 | Q4 | 29.0 est. | Yes | 0.007 |
| MacBook Pro M3 Max 128GB | 128 | Q4 | 21.2 est. | Yes | 0.005 |
| Mac Studio M2 Ultra 192GB | 192 | FP16 | 20.7 est. | No | 0.003 |
| RTX 4090 24GB | 24 | Q4 | 18.3 est. | No | 0.011 |
| RTX 4090D 24GB (China) | 24 | Q4 | 18.3 est. | No | 0.011 |
| RTX 3090 Ti 24GB | 24 | Q4 | 18.3 est. | No | 0.009 |
| RX 7900 XTX 24GB | 24 | Q4 | 17.4 est. | No | 0.017 |
| RTX 3090 24GB | 24 | Q4 | 17.0 est. | No | 0.011 |
| H100 80GB SXM5 | 80 | FP16 | 15.1 est. | No | 0.001 |
| RX 7900 XT 20GB | 20 | Q4 | 10.1 est. | No | 0.011 |
| A100 80GB SXM4 | 80 | FP16 | 9.2 est. | No | 0.001 |
| MacBook Pro M4 Max 128GB | 128 | FP16 | 6.3 est. | No | 0.001 |
| Mac Studio M3 Ultra 96GB | 96 | FP16 | 5.3 est. | No | 0.001 |
| MacBook Pro M3 Max 128GB | 128 | FP16 | 4.6 est. | No | 0.001 |
| Mac mini M4 32GB | 32 | Q4 | 3.9 est. | No | 0.004 |
| Mac mini M4 Pro 64GB | 64 | FP16 | 0.8 est. | No | 0.0 |