# Can the Tesla P40 run WeMM-Video-9B?

> Yes. The Tesla P40 runs WeMM-Video-9B fully in VRAM at FP16 / BF16 (about 22 GB of 24 GB), at roughly 9.1 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 | 4.87 | fits | 55 |
| Q3_K_M | Noticeable loss | 6.51 | fits | 37 |
| Q4_K_M | Small loss | 7.72 | fits | 30 |
| Q5_K_M | Near-lossless | 8.8 | fits | 26 |
| Q6_K | Near-lossless | 9.95 | fits | 22 |
| Q8_0 | Lossless | 12.4 | fits | 17 |
| F16 (pick) | Lossless | 22.01 | fits | 9.1 |

## Vision models that fit comfortably

- [Qwen/Qwen3.5-9B](https://selfhost.directory/models/qwen/qwen3.5-9b/on/tesla-p40): Q8_0 ≈10.81 GB, est. 19 tok/s
- [Qwen/Qwen3-VL-8B-Instruct](https://selfhost.directory/models/qwen/qwen3-vl-8b-instruct/on/tesla-p40): Q8_0 ≈10.15 GB, est. 20 tok/s
- [google/gemma-3-12b-it](https://selfhost.directory/models/google/gemma-3-12b-it/on/tesla-p40): Q8_0 ≈15.54 GB, est. 15 tok/s
- [Qwen/Qwen2.5-VL-7B-Instruct](https://selfhost.directory/models/qwen/qwen2.5-vl-7b-instruct/on/tesla-p40): Q8_0 ≈8.86 GB, est. 22 tok/s
- [XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B](https://selfhost.directory/models/xiaomimimo/mimo-v2.6-distill-qwen-9b/on/tesla-p40): Q8_0 ≈10.83 GB, est. 19 tok/s
- [meta-llama/Llama-3.2-11B-Vision-Instruct](https://selfhost.directory/models/meta-llama/llama-3.2-11b-vision-instruct/on/tesla-p40): Q8_0 ≈11.91 GB, est. 17 tok/s

## Other GPUs that run it

- [GeForce RTX 4060](https://selfhost.directory/models/tencent/wemm-video-9b/on/rtx-4060): Q3_K_M, est. 29 tok/s
- [Apple M4 (16 GB)](https://selfhost.directory/models/tencent/wemm-video-9b/on/apple-m4-16gb): Q6_K, est. 7.6 tok/s
- [Radeon RX 6700 XT](https://selfhost.directory/models/tencent/wemm-video-9b/on/rx-6700-xt): Q6_K, est. 24 tok/s
- [GeForce RTX 3060 12GB](https://selfhost.directory/models/tencent/wemm-video-9b/on/rtx-3060): Q6_K, est. 23 tok/s
- [Arc B580](https://selfhost.directory/models/tencent/wemm-video-9b/on/arc-b580): Q6_K, est. 29 tok/s
- [Tesla T4](https://selfhost.directory/models/tencent/wemm-video-9b/on/tesla-t4): Q8_0, est. 16 tok/s
- [Arc A770 16GB](https://selfhost.directory/models/tencent/wemm-video-9b/on/arc-a770): Q8_0, est. 28 tok/s
- [Radeon RX 7800 XT](https://selfhost.directory/models/tencent/wemm-video-9b/on/rx-7800-xt): Q8_0, est. 31 tok/s

---
Model: https://selfhost.directory/models/tencent/wemm-video-9b. GPU: https://selfhost.directory/models/gpus/tesla-p40. Source: https://selfhost.directory/models/tencent/wemm-video-9b/on/tesla-p40