Explore models.

Nemotron 3.5 Super VL

120B/12B-active Mamba-2 hybrid with a vision encoder; native speculative decoding and switchable thinking.

NVIDIA: Nemotron 3.5 Lightning

NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that...

Cosmos3-Super-Text2Image-4Step

Nemotron-3-Embed-1B-BF16

Nemotron-3-Embed-1B-BF16 is a compact multilingual text embedding model from NVIDIA, pruned and distilled from Ministral-3 to ~1B parameters, that maps text into 2048-dimensional dense vectors for retrieval…

Cosmos3-Super-Text2Image

Cosmos3-Super-Text2Image (agentic)

NVIDIA: Parakeet TDT 0.6B v3

Parakeet TDT 0.6B v3 is NVIDIA's 600M-parameter multilingual speech-to-text model built on the FastConformer-TDT architecture. Trained on the Granary dataset (670,000+ hours of audio), it supports automatic…

Magpie-Multilingual 357M (Feb 2026)

nvidia/canary-1b-v2

1B parameters · 25 languages · Encoder: Conformer-based · Decoder: Transformer

nvidia/canary-qwen-2.5b

2.5B parameters · Encoder: Conformer-based · Decoder: Qwen2

nvidia/nemotron-3.5-asr-streaming-0.6b

0.64B parameters · 40 languages · Encoder: FastConformer (cache-aware) · Decoder: RNNT

nvidia/nemotron-speech-streaming-en-0.6b

0.62B parameters · Encoder: FastConformer (cache-aware) · Decoder: RNNT

nvidia/parakeet-ctc-1.1b

1.1B parameters · Encoder: Conformer-based · Decoder: CTC

nvidia/parakeet-tdt-0.6b-v2

0.6B parameters · Encoder: Conformer-based · Decoder: TDT / RNN-T

nvidia/parakeet-tdt-0.6b-v2 (fast-gpu-asr)

0.6B parameters · Encoder: Conformer-based · Decoder: TDT

nvidia/parakeet-tdt-0.6b-v3 (fast-gpu-asr)

0.6B parameters · 26 languages · Encoder: Conformer-based · Decoder: TDT

Nemotron 3 Ultra