# Can the Instinct MI50 32GB run Apriel-Voice-27B-preview?

> Yes. The Instinct MI50 32GB runs Apriel-Voice-27B-preview fully in VRAM at Q6_K (about 24 GB of 32 GB), at roughly 25 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 | 11.13 | fits | 63 |
| Q3_K_M | Noticeable loss | 15.39 | fits | 42 |
| Q4_K_M | Small loss | 18.52 | fits | 34 |
| Q5_K_M | Near-lossless | 21.31 | fits | 29 |
| Q6_K (pick) | Near-lossless | 24.31 | fits | 25 |
| Q8_0 | Lossless | 30.67 | tight | 19 |
| F16 | Lossless | 55.63 | offload | 1.3 |

## Omni models that fit comfortably

- [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
- [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
- [Qwen/Qwen3-Omni-30B-A3B-Thinking](https://selfhost.directory/models/qwen/qwen3-omni-30b-a3b-thinking/on/instinct-mi50): Q6_K ≈26.8 GB, est. 228 tok/s
- [nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16](https://selfhost.directory/models/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning-bf16/on/instinct-mi50): Q6_K ≈27.5 GB, est. 228 tok/s
- [Qwen/Qwen3-Omni-30B-A3B-Captioner](https://selfhost.directory/models/qwen/qwen3-omni-30b-a3b-captioner/on/instinct-mi50): Q6_K ≈26.8 GB, est. 228 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

## Other GPUs that run it

- [Tesla T4](https://selfhost.directory/models/servicenow-ai/apriel-voice-27b-preview/on/tesla-t4): Q3_K_M, est. 13 tok/s
- [Arc A770 16GB](https://selfhost.directory/models/servicenow-ai/apriel-voice-27b-preview/on/arc-a770): Q3_K_M, est. 23 tok/s
- [Radeon RX 7800 XT](https://selfhost.directory/models/servicenow-ai/apriel-voice-27b-preview/on/rx-7800-xt): Q3_K_M, est. 26 tok/s
- [Tesla P40](https://selfhost.directory/models/servicenow-ai/apriel-voice-27b-preview/on/tesla-p40): Q5_K_M, est. 9.9 tok/s
- [Radeon RX 7900 XTX](https://selfhost.directory/models/servicenow-ai/apriel-voice-27b-preview/on/rx-7900-xtx): Q5_K_M, est. 27 tok/s
- [GeForce RTX 5090](https://selfhost.directory/models/servicenow-ai/apriel-voice-27b-preview/on/rtx-5090): Q6_K, est. 44 tok/s
- [Apple M4 Pro (48 GB)](https://selfhost.directory/models/servicenow-ai/apriel-voice-27b-preview/on/apple-m4-pro-48gb): Q8_0, est. 5.2 tok/s
- [RTX A6000](https://selfhost.directory/models/servicenow-ai/apriel-voice-27b-preview/on/rtx-a6000): Q8_0, est. 15 tok/s

---
Model: https://selfhost.directory/models/servicenow-ai/apriel-voice-27b-preview. GPU: https://selfhost.directory/models/gpus/instinct-mi50. Source: https://selfhost.directory/models/servicenow-ai/apriel-voice-27b-preview/on/instinct-mi50