{"work":{"id":"a449edca-bc6c-4333-9b98-84c9578290bf","openalex_id":"https://openalex.org/W4416050145","doi":"10.48550/arxiv.2508.14444","arxiv_id":"2508.14444","raw_key":null,"title":"NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model","authors":null,"authors_text":"NVIDIA: Aarti Basant, Abhijit Khairnar, Abhijit Paithankar, Abhinav Khattar, Adithya Renduchintala, Aditya Malte","year":2025,"venue":"cs.CL","abstract":"We introduce Nemotron-Nano-9B-v2, a hybrid Mamba-Transformer language model designed to increase throughput for reasoning workloads while achieving state-of-the-art accuracy compared to similarly-sized models. Nemotron-Nano-9B-v2 builds on the Nemotron-H architecture, in which the majority of the self-attention layers in the common Transformer architecture are replaced with Mamba-2 layers, to achieve improved inference speed when generating the long thinking traces needed for reasoning. We create Nemotron-Nano-9B-v2 by first pre-training a 12-billion-parameter model (Nemotron-Nano-12B-v2-Base) on 20 trillion tokens using an FP8 training recipe. After aligning Nemotron-Nano-12B-v2-Base, we employ the Minitron strategy to compress and distill the model with the goal of enabling inference on up to 128k tokens on a single NVIDIA A10G GPU (22GiB of memory, bfloat16 precision). Compared to existing similarly-sized models (e.g., Qwen3-8B), we show that Nemotron-Nano-9B-v2 achieves on-par or better accuracy on reasoning benchmarks while achieving up to 6x higher inference throughput in reasoning settings like 8k input and 16k output tokens. We are releasing Nemotron-Nano-9B-v2, Nemotron-Nano12B-v2-Base, and Nemotron-Nano-9B-v2-Base checkpoints along with the majority of our pre- and post-training datasets on Hugging Face.","external_url":"https://arxiv.org/abs/2508.14444","cited_by_count":0,"metadata_source":"pith","metadata_fetched_at":"2026-08-05T02:28:24.338817+00:00","pith_arxiv_id":"2508.14444","created_at":"2026-05-11T04:50:54.943685+00:00","updated_at":"2026-08-05T02:28:24.338817+00:00","title_quality_ok":true,"display_title":"NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model","render_title":"NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model"},"hub":{"state":{"work_id":"a449edca-bc6c-4333-9b98-84c9578290bf","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":33,"external_cited_by_count":0,"distinct_field_count":5,"first_pith_cited_at":"2025-04-16T21:36:46+00:00","last_pith_cited_at":"2026-07-08T17:59:59+00:00","author_build_status":"not_needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"not_needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-08-22T09:29:31.294984+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":4},{"context_role":"baseline","n":1},{"context_role":"dataset","n":1}],"polarity_counts":[{"context_polarity":"background","n":4},{"context_polarity":"baseline","n":1},{"context_polarity":"use_dataset","n":1}],"runs":{},"summary":{},"graph":{},"authors":[]}}