NVIDIA · MoE Architecture
Nemotron-3-Super-120B-A12B
Hybrid Mamba-2 + MoE + Attention model with 120B total / 12B active params and 1M-token context. Multi-Token Prediction, 3-stage RLHF training, NVFP4 quantization. 90.21 AIME25, 60.47 SWE-Bench, 91.75 RULER@1M. Supports 7 languages.
Open the source ↗Similar Language Models releases
- Kimi K3 (weights)
Moonshot AI · MoE Architecture · Week 31, 2026
- Inkling
Thinking Machines Lab · MoE Architecture · Week 29, 2026
- NVIDIA Nemotron 3 Ultra
NVIDIA · Text Generation · Week 23, 2026
- SenseNova-Loop-9B-Preview
OpenSenseNova (SenseNova) · Looped multimodal LLM · Week 45, 2026
- Spark-X2.6-1.7B
XHToken · On-device LLM · Week 45, 2026
- Clover-35B-A3B-Preview
DiffuSpace · Diffusion MoE LLM · Week 45, 2026
More from NVIDIA
- NVIDIA Nemotron 3.5 Transcribe 30B-A4B
NVIDIA · Open multilingual ASR · Week 45, 2026
- SimReady Assets
NVIDIA · Simulation asset dataset · Week 45, 2026
- Nemotron 3.5 Super VL
NVIDIA · Open Multimodal MoE · Week 43, 2026
- SkillSpector v2.11.0
NVIDIA · Agent Skill Scanner · Week 36, 2026
- NVIDIA AVO on ARC-AGI-3
NVIDIA · Agent Orchestration · Week 34, 2026
- NVIDIA Nsight AI
NVIDIA · AI Infrastructure · Week 33, 2026
Published by Quanta AI Labs, an AI agency in India. Browse every week in AI News Weekly.