InternVL3 models

4 InternVL3 models from OpenGVLab on Hugging Face, from 938M to 78.4B parameters, published by OpenGVLab in BF16, with a 32K-token context. The smallest official model, InternVL3-1B, needs about 2.1 GB of VRAM at its published precision; the cheapest live fit is RTX 3070 at $0.088/hr.

Part of the InternVL series · Previous generation: InternVL2

Pick a size

One row per official InternVL3 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
InternVL3-1B938M2.1 GB1.0 GB0.5 GBRTX 3070$0.088/hrnot published for this architecture
InternVL3-8B7.9B17.8 GB8.9 GB4.4 GBRTX A5000$0.176/hrnot published for this architecture
InternVL3-78B78.4B175 GB87.6 GB43.8 GBAMD MI300X$2.63/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
InternVL3-1B938MBF162.1 GBRTX 3070$0.088/hr
InternVL3-1B-hf938MBF162.1 GBRTX 3070$0.088/hr
InternVL3-8B7.9BBF1617.8 GBRTX A5000$0.176/hr
InternVL3-78B78.4BBF16175 GBAMD MI300X$2.63/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 OpenGVLab

Start ComfyUI on a rented GPU.

© 2026 Aquanode. All rights reserved.

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