Nemotron 3
NVIDIA-Nemotron-3-Super-120B-A12B-BF16
NVIDIA · open-restricted nvidia-nemotron-open-model-license
| Parameters (B) | 123.611 |
|---|---|
| Architecture | moe |
| Layers / KV heads / head dim | 88 / 2 / 128 |
| Context window | 262144 |
| Modalities | in: text; out: text |
| GGUF | available |
| Commercial use | yes |
Minimum hardware (estimate)
At Q4_K_M and 8k context, total working set ≈ 76.3 GiB. On a machine with 64 GiB system RAM and no discrete GPU: Won't run. Limiting factor: No GPU and system RAM insufficient for weights + KV.
Scores
No Tier A comparable scores ingested yet for this model.
Provenance
- identity, license, architecture, parameter count: https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16 (retrieved 2026-08-10)
HF: nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16 · snapshot 2026-08-10