# Can the Instinct MI50 32GB run NLD-Uni?

> Yes. The Instinct MI50 32GB runs NLD-Uni fully in VRAM at Q8_0 (about 21 GB of 32 GB), at roughly 29 tokens/s.

Instinct MI50 32GB: 32 GB (32 GB usable), 1024 GB/s. Estimates at an 8K context.

## Every quantisation

| Quant | Quality | ≈ GB | Fit | Est. tok/s |
|---|---|---|---|---|
| Q2_K | Heavy loss | 7.44 | fits | 94 |
| Q3_K_M | Noticeable loss | 10.29 | fits | 63 |
| Q4_K_M | Small loss | 12.39 | fits | 51 |
| Q5_K_M | Near-lossless | 14.27 | fits | 43 |
| Q6_K | Near-lossless | 16.28 | fits | 37 |
| Q8_0 (pick) | Lossless | 20.54 | fits | 29 |
| F16 | Lossless | 37.29 | offload | 4.7 |

## Omni models that fit comfortably

- [sensenova/SenseNova-U1.5-8B-MoT](https://selfhost.directory/models/sensenova/sensenova-u1.5-8b-mot/on/instinct-mi50): Q8_0 ≈20.03 GB, est. 30 tok/s
- [google/gemma-4-12B-it](https://selfhost.directory/models/google/gemma-4-12b-it/on/instinct-mi50): Q8_0 ≈15.89 GB, est. 44 tok/s
- [mistralai/Voxtral-Small-24B-2507](https://selfhost.directory/models/mistralai/voxtral-small-24b-2507/on/instinct-mi50): Q8_0 ≈26.25 GB, est. 22 tok/s
- [ByteDance-Seed/BAGEL-7B-MoT](https://selfhost.directory/models/bytedance-seed/bagel-7b-mot/on/instinct-mi50): Q8_0 ≈16.51 GB, est. 36 tok/s
- [Qwen/Qwen2.5-Omni-7B](https://selfhost.directory/models/qwen/qwen2.5-omni-7b/on/instinct-mi50): Q8_0 ≈8.86 GB, est. 49 tok/s
- [Qwen/Qwen3-Omni-30B-A3B-Instruct](https://selfhost.directory/models/qwen/qwen3-omni-30b-a3b-instruct/on/instinct-mi50): Q6_K ≈29.65 GB, est. 228 tok/s

## Other GPUs that run it

- [Apple M4 (16 GB)](https://selfhost.directory/models/nvidia/nld-uni/on/apple-m4-16gb): Q3_K_M, est. 7.4 tok/s
- [Radeon RX 6700 XT](https://selfhost.directory/models/nvidia/nld-uni/on/rx-6700-xt): Q3_K_M, est. 24 tok/s
- [GeForce RTX 3060 12GB](https://selfhost.directory/models/nvidia/nld-uni/on/rtx-3060): Q3_K_M, est. 22 tok/s
- [Arc B580](https://selfhost.directory/models/nvidia/nld-uni/on/arc-b580): Q3_K_M, est. 28 tok/s
- [Tesla T4](https://selfhost.directory/models/nvidia/nld-uni/on/tesla-t4): Q5_K_M, est. 14 tok/s
- [Arc A770 16GB](https://selfhost.directory/models/nvidia/nld-uni/on/arc-a770): Q5_K_M, est. 24 tok/s
- [Radeon RX 7800 XT](https://selfhost.directory/models/nvidia/nld-uni/on/rx-7800-xt): Q5_K_M, est. 26 tok/s
- [Tesla P40](https://selfhost.directory/models/nvidia/nld-uni/on/tesla-p40): Q8_0, est. 9.8 tok/s

---
Model: https://selfhost.directory/models/nvidia/nld-uni. GPU: https://selfhost.directory/models/gpus/instinct-mi50. Source: https://selfhost.directory/models/nvidia/nld-uni/on/instinct-mi50