# Can the Arc B580 run NLD-Uni?

> Yes, but only at Q3_K_M (about 10 GB of 12 GB), which costs noticeable quality, at roughly 28 tokens/s.

Arc B580: 12 GB (12 GB usable), 456 GB/s. Estimates at an 8K context.

## Every quantisation

| Quant | Quality | ≈ GB | Fit | Est. tok/s |
|---|---|---|---|---|
| Q2_K | Heavy loss | 7.44 | fits | 42 |
| Q3_K_M (pick) | Noticeable loss | 10.29 | fits | 28 |
| Q4_K_M | Small loss | 12.39 | offload | 19 |
| Q5_K_M | Near-lossless | 14.27 | offload | 9.4 |
| Q6_K | Near-lossless | 16.28 | offload | 6.1 |
| Q8_0 | Lossless | 20.54 | offload | 3.5 |
| F16 | Lossless | 37.29 | no | — |

## Omni models that fit comfortably

- [google/gemma-4-12B-it](https://selfhost.directory/models/google/gemma-4-12b-it/on/arc-b580): Q4_K_M ≈10.46 GB, est. 35 tok/s
- [ByteDance-Seed/BAGEL-7B-MoT](https://selfhost.directory/models/bytedance-seed/bagel-7b-mot/on/arc-b580): Q5_K_M ≈11.32 GB, est. 24 tok/s
- [Qwen/Qwen2.5-Omni-7B](https://selfhost.directory/models/qwen/qwen2.5-omni-7b/on/arc-b580): Q8_0 ≈8.86 GB, est. 22 tok/s
- [google/gemma-4-12B](https://selfhost.directory/models/google/gemma-4-12b/on/arc-b580): Q4_K_M ≈10.59 GB, est. 35 tok/s
- [inclusionAI/LLaDA2.0-Uni](https://selfhost.directory/models/inclusionai/llada2.0-uni/on/arc-b580): Q4_K_M ≈10.49 GB, est. 276 tok/s
- [openbmb/MiniCPM-o-4_5](https://selfhost.directory/models/openbmb/minicpm-o-4_5/on/arc-b580): Q8_0 ≈10.15 GB, est. 25 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
- [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
- [Radeon RX 7900 XTX](https://selfhost.directory/models/nvidia/nld-uni/on/rx-7900-xtx): Q8_0, est. 27 tok/s

---
Model: https://selfhost.directory/models/nvidia/nld-uni. GPU: https://selfhost.directory/models/gpus/arc-b580. Source: https://selfhost.directory/models/nvidia/nld-uni/on/arc-b580