ServiceNow-AI models
1 ServiceNow-AI model from ServiceNow-AI on Hugging Face, from 27.2B to 27.2B parameters, published by ServiceNow-AI in BF16. The smallest official model, Apriel-Voice-27B-preview, needs about 60.9 GB of VRAM at its published precision; the cheapest live fit is RTX PRO 6000 at $1.38/hr.
Pick a size
One row per official ServiceNow-AI size: the VRAM it needs at each precision, the cheapest GPU that holds it today, and the KV cache for a 32K-token context.
| Model | Parameters | Native VRAM | FP8 VRAM | INT4 VRAM | Live GPU fit (native) | Est. $/hr | KV cache at 32K |
|---|---|---|---|---|---|---|---|
| Apriel-Voice-27B-preview | 27.2B | 60.9 GB | 30.4 GB | 15.2 GB | RTX PRO 6000 | $1.38/hr | not published for this architecture |
VRAM is weights times a flat 1.2 overhead; the KV cache is a separate per-model figure at 16-bit, shown where the architecture is published. See the methodology.
Official models (1)
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| Apriel-Voice-27B-preview | 27.2B | BF16 | 60.9 GB | RTX PRO 6000 | $1.38/hr |
VRAM is for the precision the model is published in: the weights times a flat 1.2 overhead, with the KV cache not included. See the methodology. The fit shown is the lowest-priced single GPU type that holds the model at that precision, or the lowest-priced multi-GPU set (up to 8) when none does.
