Infomaniak-AI models
1 Infomaniak-AI model from Infomaniak-AI on Hugging Face, from 5.0B to 5.0B parameters, published by Infomaniak-AI in BF16, with a 128K-token context. The smallest official model, vllm-translategemma-4b-it, needs about 11.1 GB of VRAM at its published precision; the cheapest live fit is RTX 5060 Ti at $0.165/hr.
Pick a size
One row per official Infomaniak-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 |
|---|---|---|---|---|---|---|---|
| vllm-translategemma-4b-it | 5.0B | 11.1 GB | 5.6 GB | 2.8 GB | RTX 5060 Ti | $0.165/hr | 0.74 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)
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| vllm-translategemma-4b-it | 5.0B | BF16 | 11.1 GB | RTX 5060 Ti | $0.165/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.