SYLIN

Nemotron

Family · 5 entries

Nemotron, side by side

NameWhat to knowPrice or memoryRanks
Nemotron 3.5 LightningModelNVIDIA released Nemotron 3.5 Lightning, a 30B mixture-of-experts model with 3B active parameters per token~75 GB
Nemotron TranscribeModelNvidia 34B (4.3B active) ASR: 40 languages, hour-long audio, diarization, word timestamps, style control; BF16 67.5 GB, FP4 under 22 GB~67.5 GB
Nemotron SuperModelNvidia Nemotron 3.5 Super VL: multimodal 120B MoE (12B active), over 600 tokens/s, open weights with training recipe, about 75 GB~75 GB
Nemotron-Labs-DiffusionModelCited as NVIDIA's recent diffusion language model work
Nemotron EmbedModelRanked first at the 1B scale on the retrieval leaderboard, scoring 72.4% (RTEB), a 27% error reduction over its predecessor~16 GB