# NVIDIA-NemotronLabs-AI-for-Media-Sports-Basketball

> NVIDIA-NemotronLabs-AI-for-Media-Sports-Basketball is a fine-tuned multimodal large language model derived from Nemotron 3 Nano Omni.

- **Organisation:** nvidia
- **Category:** Omni / Any-to-Any
- **Parameters:** 33B
- **Context length:** 262,144 tokens
- **Licence:** openmdw-1.1 (Commercial use OK)
- **Released:** 2026-09-17
- **Hugging Face:** 1.2K downloads (30 days), 9 likes

## Estimated memory

| Quant | ≈ GB |
|---|---|
| Q2_K | 11.52 |
| Q3_K_M | 16.69 |
| Q4_K_M | 20.48 |
| Q5_K_M | 23.87 |
| Q6_K | 27.5 |
| Q8_0 | 35.21 |
| F16 | 65.48 |

## Runs with

- [SGLang](https://selfhost.directory/project/sglang)
- [Transformers](https://github.com/huggingface/transformers)
- [vLLM](https://selfhost.directory/project/vllm)

## About

NVIDIA-NemotronLabs-AI-for-Media-Sports-Basketball is a fine-tuned multimodal large language model derived from Nemotron 3 Nano Omni. It was further trained on Q&A pairs generated from BARD, a public dataset of play-level basketball broadcast video clips with human-validated annotations, to specialize in basketball play understanding. The model supports structured multiple-choice and open-ended Q&A over play clips, covering player actions, shot mechanics and outcomes, rebounding, play structure, player identification (jersey numbers and team colours), and structured play captioning. It works best when a full basketball play clip is passed as input.

This model is fine-tuned from Nemotron 3 Nano Omni on Q&A pairs generated from the public BARD dataset (Basketball Action Recognition Dataset, CC BY 4.0) of basketball play video clips using the NVIDIA Sports Intelligence playbooks. For base model details, see the base model card.

This model is ready for commercial or non-commercial use.

## Alternatives

- [nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16](https://selfhost.directory/models/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning-bf16) (33B (3B active), nvidia-open-model-agreement, ≈20.48 GB at Q4): 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.
- [Qwen/Qwen3-Omni-30B-A3B-Instruct](https://selfhost.directory/models/qwen/qwen3-omni-30b-a3b-instruct) (35.3B (3B active), Apache 2.0, ≈22.15 GB at Q4): Qwen3-Omni is the natively end-to-end multilingual omni-modal foundation models. It processes text, images, audio, and video, and delivers real-time streaming responses in both text and natural speech. We introduce several architectural upgrades to improve performance and efficiency. Key features:
- [Qwen/Qwen3-Omni-30B-A3B-Thinking](https://selfhost.directory/models/qwen/qwen3-omni-30b-a3b-thinking) (31.7B (3B active), Apache 2.0, ≈20.05 GB at Q4): Qwen3-Omni is the natively end-to-end multilingual omni-modal foundation models. It processes text, images, audio, and video, and delivers real-time streaming responses in both text and natural speech. We introduce several architectural upgrades to improve performance and efficiency. Key features:
- [nvidia/NVIDIA-NemotronLabs-AI-for-Media-Sports-Tennis](https://selfhost.directory/models/nvidia/nvidia-nemotronlabs-ai-for-media-sports-tennis) (33B, openmdw-1.1, ≈20.48 GB at Q4): NVIDIA-NemotronLabs-AI-for-Media-Sports-Tennis is a fine-tuned multimodal large language model derived from Nemotron 3 Nano Omni. It was further trained on an in-house NVIDIA tennis dataset of manually labeled point-level video clips to specialize in tennis match understanding.
- [ServiceNow-AI/Apriel-Voice-27B-preview](https://selfhost.directory/models/servicenow-ai/apriel-voice-27b-preview) (27.2B, MIT, ≈18.52 GB at Q4): An open model for speech, reasoning, and tool use from ServiceNow
- [Qwen/Qwen3-Omni-30B-A3B-Captioner](https://selfhost.directory/models/qwen/qwen3-omni-30b-a3b-captioner) (31.7B (3B active), Apache 2.0, ≈20.05 GB at Q4): Since the research community currently lacks a general-purpose audio captioning model, we fine-tuned Qwen3-Omni-30B-A3B to obtain Qwen3-Omni-30B-A3B-Captioner, which produces detailed, low-hallucination captions for arbitrary audio inputs.

More: https://selfhost.directory/models/nvidia/nvidia-nemotronlabs-ai-for-media-sports-basketball/alternatives

## Runs well on

- [Tesla P40](https://selfhost.directory/models/nvidia/nvidia-nemotronlabs-ai-for-media-sports-basketball/on/tesla-p40): Q4_K_M, est. 9.5 tok/s
- [Radeon RX 7900 XTX](https://selfhost.directory/models/nvidia/nvidia-nemotronlabs-ai-for-media-sports-basketball/on/rx-7900-xtx): Q4_K_M, est. 26 tok/s
- [Instinct MI50 32GB](https://selfhost.directory/models/nvidia/nvidia-nemotronlabs-ai-for-media-sports-basketball/on/instinct-mi50): Q6_K, est. 21 tok/s
- [GeForce RTX 5090](https://selfhost.directory/models/nvidia/nvidia-nemotronlabs-ai-for-media-sports-basketball/on/rtx-5090): Q6_K, est. 36 tok/s
- [Apple M4 Pro (48 GB)](https://selfhost.directory/models/nvidia/nvidia-nemotronlabs-ai-for-media-sports-basketball/on/apple-m4-pro-48gb): Q6_K, est. 5.5 tok/s
- [RTX A6000](https://selfhost.directory/models/nvidia/nvidia-nemotronlabs-ai-for-media-sports-basketball/on/rtx-a6000): Q8_0, est. 12 tok/s

## Similar size

- [Qwen/Qwen3-Omni-30B-A3B-Instruct](https://selfhost.directory/models/qwen/qwen3-omni-30b-a3b-instruct) (35.3B)
- [nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16](https://selfhost.directory/models/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning-bf16) (33B)
- [Qwen/Qwen3-Omni-30B-A3B-Thinking](https://selfhost.directory/models/qwen/qwen3-omni-30b-a3b-thinking) (31.7B)
- [mistralai/Voxtral-Small-24B-2507](https://selfhost.directory/models/mistralai/voxtral-small-24b-2507) (24.3B)
- [Qwen/Qwen3-Omni-30B-A3B-Captioner](https://selfhost.directory/models/qwen/qwen3-omni-30b-a3b-captioner) (31.7B)
- [ServiceNow-AI/Apriel-Voice-27B-preview](https://selfhost.directory/models/servicenow-ai/apriel-voice-27b-preview) (27.2B)

## FAQ

**How much VRAM does NVIDIA-NemotronLabs-AI-for-Media-Sports-Basketball need?**
About 20 GB at Q4_K_M with an 8K context. Q8_0 needs about 35 GB and full precision about 65 GB. Longer contexts need more memory for the KV cache.

**Can NVIDIA-NemotronLabs-AI-for-Media-Sports-Basketball run on the Tesla P40?**
Yes. It fits at Q4_K_M (about 20 GB), at an estimated 9.5 tokens/s. It fits comfortably on the Radeon RX 7900 XTX, Instinct MI50 32GB, RTX 5090.

**Can I use NVIDIA-NemotronLabs-AI-for-Media-Sports-Basketball commercially?**
Yes. It is released under openmdw-1.1. Custom licence: read the model card before using it commercially.

**What is the context length of NVIDIA-NemotronLabs-AI-for-Media-Sports-Basketball?**
262,144 tokens (256K). The full window needs far more memory than an 8K context.

**How do I run NVIDIA-NemotronLabs-AI-for-Media-Sports-Basketball locally?**
With vLLM: vllm serve nvidia/NVIDIA-NemotronLabs-AI-for-Media-Sports-Basketball.

## Links

- huggingface: https://huggingface.co/nvidia/NVIDIA-NemotronLabs-AI-for-Media-Sports-Basketball
- github: https://github.com/NVIDIA/sports-intelligence-playbooks

---
Source: https://selfhost.directory/models/nvidia/nvidia-nemotronlabs-ai-for-media-sports-basketball