Nemotron 3 Super 120B-A12B — 120B Parameter Mixture of Experts LLM
Model Specifications
- Parameters
- 120B (12B active)
- Architecture
- Mixture of Experts
- Context Length
- 977K tokens
- Capabilities
- chat, coding, reasoning, agentic
- Release Date
- 2026-03-11
- Provider
- NVIDIA
- Family
- nemotron
VRAM Requirements
| Quantization | BPW | VRAM | Quality |
|---|---|---|---|
| IQ2_XXS | 2.38 | 36.2 GB | 65% |
| IQ2_M | 2.93 | 44.4 GB | 75% |
| Q2_K | 3.16 | 47.9 GB | 78% |
| IQ3_XXS | 3.25 | 49.2 GB | 82% |
| Q3_K_S | 3.64 | 55.1 GB | 85% |
| Q3_K_M | 4 | 60.5 GB | 88% |
| IQ4_XS | 4.46 | 67.4 GB | 92% |
| Q4_K_S | 4.67 | 70.5 GB | 93% |
| Q4_K_M | 4.89 | 73.8 GB | 94% |
| Q5_K_S | 5.57 | 84.0 GB | 96% |
| Q5_K_M | 5.7 | 86.0 GB | 96% |
| Q6_K | 6.56 | 98.9 GB | 97% |
| Q8_0 | 8.5 | 128.0 GB | 100% |
| FP16 | 16 | 240.5 GB | 100% |
Benchmark Scores
GPQA Diamond79.2
MMLU-PRO83.7
IFEval72.6
HLE18.3
How to Run Nemotron 3 Super 120B-A12B
Run Nemotron 3 Super 120B-A12B locally with Ollama (needs 73.8 GB VRAM at Q4_K_M):
ollama run nemotron-3-super:120b-a12bCompatible GPUs (30)
GPUs that can run Nemotron 3 Super 120B-A12B at Q4_K_M quantization:
NVIDIA H100 SXM5 80GB(80GB, 3350 GB/s)NVIDIA H100 PCIe 80GB(80GB, 2000 GB/s)NVIDIA A100 SXM 80GB(80GB, 2039 GB/s)NVIDIA A100 PCIe 80GB(80GB, 1935 GB/s)NVIDIA A100 SXM4 80 GB(80GB, 2040 GB/s)NVIDIA A100 PCIe 80 GB(80GB, 1940 GB/s)NVIDIA A100X(80GB, 2040 GB/s)NVIDIA H100 PCIe 80 GB(80GB, 2040 GB/s)NVIDIA H100 SXM5 80 GB(80GB, 3360 GB/s)NVIDIA H100 CNX(80GB, 2040 GB/s)NVIDIA A800 PCIe 80 GB(80GB, 1940 GB/s)NVIDIA A800 SXM4 80 GB(80GB, 2040 GB/s)NVIDIA H800 PCIe 80 GB(80GB, 2040 GB/s)NVIDIA H800 SXM5(80GB, 3360 GB/s)NVIDIA RTX 6000D(84GB, 1570 GB/s)