# Can the Instinct MI50 32GB run InternLumina-U2?

> Yes. The Instinct MI50 32GB runs InternLumina-U2 fully in VRAM at Q8_0 (about 19 GB of 32 GB), at roughly 33 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 | 7.09 | fits | 107 |
| Q3_K_M | Noticeable loss | 9.59 | fits | 72 |
| Q4_K_M | Small loss | 11.43 | fits | 58 |
| Q5_K_M | Near-lossless | 13.08 | fits | 49 |
| Q6_K | Near-lossless | 14.84 | fits | 43 |
| Q8_0 (pick) | Lossless | 18.57 | fits | 33 |
| F16 | Lossless | 33.24 | offload | 11 |

## Omni models that fit comfortably

- [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
- [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
- [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
- [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
- [google/gemma-4-12B](https://selfhost.directory/models/google/gemma-4-12b/on/instinct-mi50): Q8_0 ≈15.89 GB, est. 44 tok/s
- [openbmb/MiniCPM-o-4_5](https://selfhost.directory/models/openbmb/minicpm-o-4_5/on/instinct-mi50): Q8_0 ≈10.15 GB, est. 57 tok/s

## Other GPUs that run it

- [Apple M4 (16 GB)](https://selfhost.directory/models/internlm/internlumina-u2/on/apple-m4-16gb): Q3_K_M, est. 8.4 tok/s
- [Radeon RX 6700 XT](https://selfhost.directory/models/internlm/internlumina-u2/on/rx-6700-xt): Q3_K_M, est. 27 tok/s
- [GeForce RTX 3060 12GB](https://selfhost.directory/models/internlm/internlumina-u2/on/rtx-3060): Q3_K_M, est. 25 tok/s
- [Arc B580](https://selfhost.directory/models/internlm/internlumina-u2/on/arc-b580): Q3_K_M, est. 32 tok/s
- [Tesla T4](https://selfhost.directory/models/internlm/internlumina-u2/on/tesla-t4): Q6_K, est. 13 tok/s
- [Arc A770 16GB](https://selfhost.directory/models/internlm/internlumina-u2/on/arc-a770): Q6_K, est. 23 tok/s
- [Radeon RX 7800 XT](https://selfhost.directory/models/internlm/internlumina-u2/on/rx-7800-xt): Q6_K, est. 26 tok/s
- [Tesla P40](https://selfhost.directory/models/internlm/internlumina-u2/on/tesla-p40): Q8_0, est. 11 tok/s

---
Model: https://selfhost.directory/models/internlm/internlumina-u2. GPU: https://selfhost.directory/models/gpus/instinct-mi50. Source: https://selfhost.directory/models/internlm/internlumina-u2/on/instinct-mi50