What GPU do I need to run Salesforce/blip-image-captioning-large?
470M parameters, published in F32. View on Hugging Face
blip-image-captioning-large is published by Salesforce on Hugging Face, with 481,398 downloads and 1,487 likes to date. It's a BlipForConditionalGeneration model built for image-to-text, published natively in F32.
VRAM required & cheapest live GPU fit
Required VRAM = weight size at each precision, plus a fixed overhead for KV-cache, activations, and fragmentation. Full formula and assumptions: methodology.
A GPU is only matched to a row if its hardware supports that precision, and the primary recommendation is always a single-GPU fit when one exists.
INT4 caveat: requires a quantized checkpoint actually published for this model, check its Hugging Face page before relying on this row.
Cheapest way to run blip-image-captioning-large at its published (F32) precision: 1× P4 on akash, at $0.032/hr per GPU ($0.032/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.
Weight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.
More Salesforce models
- blip2-opt-2.7b (3.7B, F32)
- blip2-flan-t5-xl (3.9B, F32)
- Llama-xLAM-2-8b-fc-r (8.0B, BF16)
- xLAM-8x22b-r (140.6B, BF16)
- Qwen3-0.6B (752M, BF16)
- gpt2 (137M, F32)
