GPT-2 models

8 GPT-2 models from openai-community on Hugging Face, from 110M to 1.6B parameters, published by openai-community in F32, with a 1K-token context. The smallest official model, gpt2, 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 GPT-2 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
gpt2137M0.6 GB0.2 GB0.1 GBRTX 3070$0.088/hr1.1 GB
gpt2-medium380M1.7 GB0.4 GB0.2 GBRTX 3070$0.088/hr3.0 GB
gpt2-large812M3.6 GB0.9 GB0.5 GBRTX 3070$0.088/hr5.6 GB
gpt2-xl1.6B7.2 GB1.8 GB0.9 GBRTX 3070$0.088/hr9.4 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 (4)

ModelParametersPublished asVRAM neededLive GPU fitEst. $/hr
gpt2137MF320.6 GBRTX 3070$0.088/hr
gpt2-medium380MF321.7 GBRTX 3070$0.088/hr
gpt2-large812MF323.6 GBRTX 3070$0.088/hr
gpt2-xl1.6BF327.2 GBRTX 3070$0.088/hr

Fine-tunes and community models (4)

ModelParametersPublished asVRAM neededLive GPU fitEst. $/hr
vietnamese-gpt2110MF320.5 GBRTX 3070$0.088/hr
turkish-gpt2124MF320.6 GBRTX 3070$0.088/hr
gpt2-small-dutch129MF320.6 GBRTX 3070$0.088/hr
megatron-gpt2-345m380MF160.8 GBRTX 3070$0.088/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 openai-community

Start ComfyUI on a rented GPU.

© 2026 Aquanode. All rights reserved.

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