SmolVLM models

4 SmolVLM models from Hugging Face on Hugging Face, from 256M to 2.2B parameters, published by Hugging Face in BF16 and F32, with a 8K-token context. The smallest official model, SmolVLM-256M-Instruct, needs about 0.6 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 SmolVLM 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
SmolVLM-256M-Instruct256M0.6 GB0.3 GB0.1 GBRTX 3070$0.088/hr0.70 GB
SmolVLM2-500M-Video-Instruct507M2.3 GB0.6 GB0.3 GBRTX 3070$0.088/hr1.3 GB
SmolVLM2-2.2B-Instruct2.2B10.0 GB2.5 GB1.3 GBV100$0.110/hrnot 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 (4)

ModelParametersPublished asVRAM neededLive GPU fitEst. $/hr
SmolVLM-256M-Instruct256MBF160.6 GBRTX 3070$0.088/hr
SmolVLM-500M-Instruct507MBF161.1 GBRTX 3070$0.088/hr
SmolVLM2-500M-Video-Instruct507MF322.3 GBRTX 3070$0.088/hr
SmolVLM2-2.2B-Instruct2.2BF3210.0 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.

More from Hugging Face

Start ComfyUI on a rented GPU.

© 2026 Aquanode. All rights reserved.

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