ibm-research models

2 ibm-research models from ibm-research on Hugging Face, from 3.4B to 3.5B parameters, published by ibm-research in F32, with a 4K-token context. The smallest official model, PowerMoE-3b, needs about 15.1 GB of VRAM at its published precision; the cheapest live fit is V100 at $0.110/hr.

Pick a size

One row per official ibm-research 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
PowerMoE-3b3.4B15.1 GB3.8 GB1.9 GBV100$0.110/hr2.0 GB
PowerLM-3b3.5B15.7 GB3.9 GB2.0 GBV100$0.110/hr11.3 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 (2)

ModelParametersPublished asVRAM neededLive GPU fitEst. $/hr
PowerMoE-3b3.4BF3215.1 GBV100$0.110/hr
PowerLM-3b3.5BF3215.7 GBV100$0.110/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.