# Can the Apple M4 Pro (48 GB) run Apriel-Voice-27B-preview?

> Yes. The Apple M4 Pro (48 GB) runs Apriel-Voice-27B-preview fully in unified memory at Q8_0 (about 31 GB of 36 GB), at roughly 5.2 tokens/s.

Apple M4 Pro (48 GB): 48 GB (36 GB usable), 273 GB/s. Estimates at an 8K context.

## Every quantisation

| Quant | Quality | ≈ GB | Fit | Est. tok/s |
|---|---|---|---|---|
| Q2_K | Heavy loss | 11.13 | fits | 17 |
| Q3_K_M | Noticeable loss | 15.39 | fits | 11 |
| Q4_K_M | Small loss | 18.52 | fits | 9.1 |
| Q5_K_M | Near-lossless | 21.31 | fits | 7.8 |
| Q6_K | Near-lossless | 24.31 | fits | 6.7 |
| Q8_0 (pick) | Lossless | 30.67 | fits | 5.2 |
| F16 | Lossless | 55.63 | no | — |

## Omni models that fit comfortably

- [Qwen/Qwen3-Omni-30B-A3B-Instruct](https://selfhost.directory/models/qwen/qwen3-omni-30b-a3b-instruct/on/apple-m4-pro-48gb): Q8_0 ≈33.01 GB, est. 47 tok/s
- [mistralai/Voxtral-Small-24B-2507](https://selfhost.directory/models/mistralai/voxtral-small-24b-2507/on/apple-m4-pro-48gb): Q8_0 ≈26.25 GB, est. 5.8 tok/s
- [Qwen/Qwen3-Omni-30B-A3B-Thinking](https://selfhost.directory/models/qwen/qwen3-omni-30b-a3b-thinking/on/apple-m4-pro-48gb): Q8_0 ≈33.01 GB, est. 47 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/apple-m4-pro-48gb): Q8_0 ≈33.75 GB, est. 47 tok/s
- [Qwen/Qwen3-Omni-30B-A3B-Captioner](https://selfhost.directory/models/qwen/qwen3-omni-30b-a3b-captioner/on/apple-m4-pro-48gb): Q6_K ≈26.8 GB, est. 61 tok/s
- [sensenova/SenseNova-U1.5-8B-MoT](https://selfhost.directory/models/sensenova/sensenova-u1.5-8b-mot/on/apple-m4-pro-48gb): Q8_0 ≈20.03 GB, est. 8.1 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
- [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/apple-m4-pro-48gb. Source: https://selfhost.directory/models/servicenow-ai/apriel-voice-27b-preview/on/apple-m4-pro-48gb