NVIDIA Nemotron 3.5 Lightning is an open 30B mixture-of-experts (MoE) model with 3B active parameters built for always-on agents.
192.8K Pulls 11 Tags Updated 4 weeks ago
NVIDIA Nemotron 3 Nano Omni is a multimodal large language model that unifies video, audio, image, and text understanding to support enterprise-grade Q&A, summarization, transcription, and document intelligence workflows.
670.7K Pulls 4 Tags Updated 5 months ago
NVIDIA Nemotron 3 Ultra is built for high-throughput reasoning and long-running agent workflows.
110.6K Pulls 1 Tag Updated 3 months ago
NVIDIA Nemotron 3 Super is a 120B open MoE model activating just 12B parameters to deliver maximum compute efficiency and accuracy for complex multi-agent applications.
3M Pulls 7 Tags Updated 6 months ago
Nemotron-3-Nano is a new Standard for Efficient, Open, and Intelligent Agentic Models, now updated with a 4B parameter count model.
869.3K Pulls 9 Tags Updated 6 months ago
An open 30B MoE model from NVIDIA with 3B activated parameters that delivers strong reasoning and agentic capabilities.
150.1K Pulls 3 Tags Updated 6 months ago
A commercial-friendly small language model by NVIDIA optimized for roleplay, RAG QA, and function calling.
720.8K Pulls 17 Tags Updated 2 years ago
Llama-3.1-Nemotron-70B-Instruct is a large language model customized by NVIDIA to improve the helpfulness of LLM generated responses to user queries.
632.5K Pulls 17 Tags Updated 1 year ago
OLMo 2 is a new family of 7B and 13B models trained on up to 5T tokens. These models are on par with or better than equivalently sized fully open models, and competitive with open-weight models such as Llama 3.1 on English academic benchmarks.
3.8M Pulls 9 Tags Updated 1 year ago
requant to IQ4_NL, with combined_en_huge as prompt (English + Coding focus)
35 Pulls 1 Tag Updated 4 weeks ago
20 Pulls 1 Tag Updated 2 weeks ago
1,029 Pulls 1 Tag Updated 5 months ago
Q4_K_M and BF16 quantizations of NVIDIA Nemotron Nano 9B v2, NVIDIA’s open 9B reasoning model. Q4 quantized locally from the BF16 source and tuned for a single 16 GB GPU card with maximum KV cache.
217 Pulls 3 Tags Updated 1 month ago
93 Pulls 1 Tag Updated 1 month ago
Nemotron-SEA-LION-v4.8-120B-A12B is a multilingual model which has been pretrained and instruct-tuned for the Southeast Asia region. Developed by AI Singapore and funded by National Research Foundation, Singapore.
6 Pulls 5 Tags Updated 1 week ago
HILBERT (Nemotron 4B nano— research/proofs) temperature 0.0 top_k 20 top_p 0.85 num_ctx 8192 repeat_penalty 1.0
6 Pulls 1 Tag Updated 3 weeks ago
Nemotron-SEA-LION-v4.8-30B-A3B is a multilingual model which has been pretrained and instruct-tuned for the Southeast Asia region. Developed by AI Singapore and funded by National Research Foundation, Singapore.
4 Pulls 5 Tags Updated 1 week ago
53 Pulls 1 Tag Updated 4 months ago
pulled from unsloth requant to IQ4_NL, with combined_en_huge as prompt (English + Coding focus)
29 Pulls 1 Tag Updated 1 month ago
Lightning Agent — a 32.9B Nemotron MoE model tuned for Hermes agentic workflows.
32 Pulls 1 Tag Updated 1 month ago