# Can the RTX A4000 run Apriel-Voice-27B-preview?

> Just about. At Q3_K_M it needs about 15 GB of the 16 GB available, so keep the context short, at roughly 19 tokens/s.

RTX A4000: 16 GB (16 GB usable), 448 GB/s. Estimates at an 8K context.

## Every quantisation

| Quant | Quality | ≈ GB | Fit | Est. tok/s |
|---|---|---|---|---|
| Q2_K | Heavy loss | 11.13 | fits | 28 |
| Q3_K_M (pick) | Noticeable loss | 15.39 | tight | 19 |
| Q4_K_M | Small loss | 18.52 | offload | 7.9 |
| Q5_K_M | Near-lossless | 21.31 | offload | 4.9 |
| Q6_K | Near-lossless | 24.31 | offload | 3.4 |
| Q8_0 | Lossless | 30.67 | offload | 2.1 |
| F16 | Lossless | 55.63 | no | — |

## Omni models that fit comfortably

- [sensenova/SenseNova-U1.5-8B-MoT](https://selfhost.directory/models/sensenova/sensenova-u1.5-8b-mot/on/rtx-a4000): Q6_K ≈9.32 GB, est. 17 tok/s
- [google/gemma-4-12B-it](https://selfhost.directory/models/google/gemma-4-12b-it/on/rtx-a4000): Q6_K ≈13.07 GB, est. 25 tok/s
- [ByteDance-Seed/BAGEL-7B-MoT](https://selfhost.directory/models/bytedance-seed/bagel-7b-mot/on/rtx-a4000): Q6_K ≈13.16 GB, est. 20 tok/s
- [Qwen/Qwen2.5-Omni-7B](https://selfhost.directory/models/qwen/qwen2.5-omni-7b/on/rtx-a4000): Q8_0 ≈8.86 GB, est. 22 tok/s
- [HiDream-ai/HiDream-E1-Full](https://selfhost.directory/models/hidream-ai/hidream-e1-full/on/rtx-a4000): Q5_K_M ≈14.75 GB, est. 20 tok/s
- [google/gemma-4-12B](https://selfhost.directory/models/google/gemma-4-12b/on/rtx-a4000): Q6_K ≈13.13 GB, est. 25 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
- [Instinct MI50 32GB](https://selfhost.directory/models/servicenow-ai/apriel-voice-27b-preview/on/instinct-mi50): Q6_K, est. 25 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

---
Model: https://selfhost.directory/models/servicenow-ai/apriel-voice-27b-preview. GPU: https://selfhost.directory/models/gpus/rtx-a4000. Source: https://selfhost.directory/models/servicenow-ai/apriel-voice-27b-preview/on/rtx-a4000