EuroLLM models

3 EuroLLM models from utter-project on Hugging Face, from 1.7B to 9.2B parameters, published by utter-project in BF16, with contexts from 4K to 32K tokens. The smallest official model, EuroLLM-1.7B-Instruct, needs about 3.7 GB of VRAM at its published precision; the cheapest live fit is RTX 3070 at $0.088/hr.

Pick a size

One row per official EuroLLM size: the VRAM it needs at each precision, the cheapest GPU that holds it today, and the KV cache for a 32K-token context.

ModelParametersNative VRAMFP8 VRAMINT4 VRAMLive GPU fit (native)Est. $/hrKV cache at 32K
EuroLLM-1.7B-Instruct1.7B3.7 GB1.9 GB0.9 GBRTX 3070$0.088/hr3.0 GB
EuroLLM-9B-Instruct-25129.2B20.5 GB10.2 GB5.1 GBRTX A5000$0.176/hr5.3 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 (3)

ModelParametersPublished asVRAM neededLive GPU fitEst. $/hr
EuroLLM-1.7B-Instruct1.7BBF163.7 GBRTX 3070$0.088/hr
EuroLLM-9B-Instruct9.2BBF1620.5 GBRTX A5000$0.176/hr
EuroLLM-9B-Instruct-25129.2BBF1620.5 GBRTX A5000$0.176/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.

Start ComfyUI on a rented GPU.

© 2026 Aquanode. All rights reserved.

All trademarks, logos and brand names are the property of their respective owners.