openjev models
1 openjev model from openjev on Hugging Face, from 27.4B to 27.4B parameters, published by openjev in BF16, with a 256K-token context. The smallest official model, openjev, needs about 61.1 GB of VRAM at its published precision; the cheapest live fit is A100 at $1.10/hr.
Pick a size
One row per official openjev 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 |
|---|---|---|---|---|---|---|---|
| openjev | 27.4B | 61.1 GB | 30.6 GB | 15.3 GB | A100 | $1.10/hr | 2.0 GB |
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)
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.
