# Can the NVIDIA H100 SXM 80GB run WeMM-Video-35BA3B?

> Yes. The NVIDIA H100 SXM 80GB runs WeMM-Video-35BA3B fully in VRAM at FP16 / BF16 (about 72 GB of 80 GB), at roughly 185 tokens/s.

NVIDIA H100 SXM 80GB: 80 GB (80 GB usable), 3350 GB/s. Estimates at an 8K context.

## Every quantisation

| Quant | Quality | ≈ GB | Fit | Est. tok/s |
|---|---|---|---|---|
| Q2_K | Heavy loss | 12.76 | fits | 1127 |
| Q3_K_M | Noticeable loss | 18.42 | fits | 758 |
| Q4_K_M | Small loss | 22.57 | fits | 611 |
| Q5_K_M | Near-lossless | 26.29 | fits | 521 |
| Q6_K | Near-lossless | 30.27 | fits | 450 |
| Q8_0 | Lossless | 38.71 | fits | 349 |
| F16 (pick) | Lossless | 71.88 | fits | 185 |

## Vision models that fit comfortably

- [Qwen/Qwen3.6-35B-A3B](https://selfhost.directory/models/qwen/qwen3.6-35b-a3b/on/h100-sxm): Q8_0 ≈38.1 GB, est. 578 tok/s
- [Qwen/Qwen3.5-35B-A3B](https://selfhost.directory/models/qwen/qwen3.5-35b-a3b/on/h100-sxm): Q8_0 ≈37.22 GB, est. 578 tok/s
- [google/gemma-4-31B-it](https://selfhost.directory/models/google/gemma-4-31b-it/on/h100-sxm): Q8_0 ≈39.91 GB, est. 55 tok/s
- [Qwen/Qwen3.8-27B](https://selfhost.directory/models/qwen/qwen3.8-27b/on/h100-sxm): Q8_0 ≈30.9 GB, est. 62 tok/s
- [openbmb/MiniCPM-V-4.7-35B-A3B](https://selfhost.directory/models/openbmb/minicpm-v-4.7-35b-a3b/on/h100-sxm): Q8_0 ≈37.22 GB, est. 578 tok/s
- [Qwen/Qwen3.6-27B](https://selfhost.directory/models/qwen/qwen3.6-27b/on/h100-sxm): Q8_0 ≈30.46 GB, est. 62 tok/s

## Other GPUs that run it

- [Tesla P40](https://selfhost.directory/models/tencent/wemm-video-35ba3b/on/tesla-p40): Q4_K_M, est. 63 tok/s
- [Radeon RX 7900 XTX](https://selfhost.directory/models/tencent/wemm-video-35ba3b/on/rx-7900-xtx): Q4_K_M, est. 175 tok/s
- [Instinct MI50 32GB](https://selfhost.directory/models/tencent/wemm-video-35ba3b/on/instinct-mi50): Q6_K, est. 138 tok/s
- [GeForce RTX 5090](https://selfhost.directory/models/tencent/wemm-video-35ba3b/on/rtx-5090): Q6_K, est. 241 tok/s
- [Apple M4 Pro (48 GB)](https://selfhost.directory/models/tencent/wemm-video-35ba3b/on/apple-m4-pro-48gb): Q6_K, est. 37 tok/s
- [RTX A6000](https://selfhost.directory/models/tencent/wemm-video-35ba3b/on/rtx-a6000): Q8_0, est. 80 tok/s
- [Apple M1 Max (64 GB)](https://selfhost.directory/models/tencent/wemm-video-35ba3b/on/apple-m1-max-64gb): Q8_0, est. 42 tok/s
- [NVIDIA A100 80GB](https://selfhost.directory/models/tencent/wemm-video-35ba3b/on/a100-80gb): F16, est. 113 tok/s

---
Model: https://selfhost.directory/models/tencent/wemm-video-35ba3b. GPU: https://selfhost.directory/models/gpus/h100-sxm. Source: https://selfhost.directory/models/tencent/wemm-video-35ba3b/on/h100-sxm