# Can the Tesla P40 run NVIDIA-NemotronLabs-AI-for-Media-Sports-Basketball?

> Yes. The Tesla P40 runs NVIDIA-NemotronLabs-AI-for-Media-Sports-Basketball fully in VRAM at Q4_K_M (about 20 GB of 24 GB), at roughly 9.5 tokens/s.

Tesla P40: 24 GB (24 GB usable), 347 GB/s. Estimates at an 8K context.

## Every quantisation

| Quant | Quality | ≈ GB | Fit | Est. tok/s |
|---|---|---|---|---|
| Q2_K | Heavy loss | 11.52 | fits | 18 |
| Q3_K_M | Noticeable loss | 16.69 | fits | 12 |
| Q4_K_M (pick) | Small loss | 20.48 | fits | 9.5 |
| Q5_K_M | Near-lossless | 23.87 | tight | 8.1 |
| Q6_K | Near-lossless | 27.5 | offload | 4.4 |
| Q8_0 | Lossless | 35.21 | offload | 2.2 |
| F16 | Lossless | 65.48 | no | — |

## Run it

Serve an OpenAI-compatible API (vllm):

```bash
vllm serve nvidia/NVIDIA-NemotronLabs-AI-for-Media-Sports-Basketball
```

Docker Compose (NVIDIA) (vllm):

```yaml
services:
  vllm:
    image: vllm/vllm-openai:latest
    command: nvidia/NVIDIA-NemotronLabs-AI-for-Media-Sports-Basketball
    ports:
      - "8000:8000"
    ipc: host
    volumes:
      - ~/.cache/huggingface:/root/.cache/huggingface
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
```

Serve an OpenAI-compatible API (sglang):

```bash
sglang serve nvidia/NVIDIA-NemotronLabs-AI-for-Media-Sports-Basketball --host 0.0.0.0 --port 30000
```

Docker Compose (NVIDIA) (sglang):

```yaml
services:
  sglang:
    image: lmsysorg/sglang:latest
    command: sglang serve nvidia/NVIDIA-NemotronLabs-AI-for-Media-Sports-Basketball --host 0.0.0.0 --port 30000
    ports:
      - "30000:30000"
    ipc: host
    volumes:
      - ~/.cache/huggingface:/root/.cache/huggingface
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
```


## Omni models that fit comfortably

- [Qwen/Qwen3-Omni-30B-A3B-Instruct](https://selfhost.directory/models/qwen/qwen3-omni-30b-a3b-instruct/on/tesla-p40): Q4_K_M ≈19.39 GB, est. 105 tok/s
- [nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16](https://selfhost.directory/models/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning-bf16/on/tesla-p40): Q4_K_M ≈20.48 GB, est. 105 tok/s
- [Qwen/Qwen3-Omni-30B-A3B-Thinking](https://selfhost.directory/models/qwen/qwen3-omni-30b-a3b-thinking/on/tesla-p40): Q4_K_M ≈19.39 GB, est. 105 tok/s
- [Qwen/Qwen3-Omni-30B-A3B-Captioner](https://selfhost.directory/models/qwen/qwen3-omni-30b-a3b-captioner/on/tesla-p40): Q4_K_M ≈19.39 GB, est. 105 tok/s
- [mistralai/Voxtral-Small-24B-2507](https://selfhost.directory/models/mistralai/voxtral-small-24b-2507/on/tesla-p40): Q6_K ≈20.67 GB, est. 9.5 tok/s
- [stepfun-ai/Step-Audio-R1](https://selfhost.directory/models/stepfun-ai/step-audio-r1/on/tesla-p40): Q4_K_M ≈22.45 GB, est. 9.4 tok/s

## Other GPUs that run it

- [GeForce RTX 3090](https://selfhost.directory/models/nvidia/nvidia-nemotronlabs-ai-for-media-sports-basketball/on/rtx-3090): Q4_K_M, est. 26 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
- [Apple M1 Max (64 GB)](https://selfhost.directory/models/nvidia/nvidia-nemotronlabs-ai-for-media-sports-basketball/on/apple-m1-max-64gb): Q8_0, est. 6.3 tok/s
- [NVIDIA A100 80GB](https://selfhost.directory/models/nvidia/nvidia-nemotronlabs-ai-for-media-sports-basketball/on/a100-80gb): F16, est. 17 tok/s

---
Model: https://selfhost.directory/models/nvidia/nvidia-nemotronlabs-ai-for-media-sports-basketball. GPU: https://selfhost.directory/models/gpus/tesla-p40. Source: https://selfhost.directory/models/nvidia/nvidia-nemotronlabs-ai-for-media-sports-basketball/on/tesla-p40