What GPU do I need to run ATH-MaaS/Ovis2.5-9B?
9.2B parameters, published in BF16. View on Hugging Face
Ovis2.5-9B is published by ATH-MaaS on Hugging Face, with 370,892 downloads and 308 likes to date. It's a Ovis2_5 model built for image-text-to-text, published natively in BF16.
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 Ovis2.5-9B at its published (BF16) precision: 1× RTX 3090 on simplepod, at $0.160/hr per GPU ($0.160/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 ATH-MaaS models
- Qwen3-0.6B (752M, BF16)
- Qwen3-8B (8.2B, BF16)
- Qwen2.5-1.5B-Instruct (1.5B, BF16)
- gpt2 (137M, F32)
- Qwen2.5-7B-Instruct (7.6B, BF16)
- Llama-3.2-1B-Instruct (1.2B, BF16)
