What GPU do I need to run h2oai/h2ovl-mississippi-800m?
826M parameters, published in BF16. View on Hugging Face
Set up h2ovl-mississippi-800mh2ovl-mississippi-800m is published by h2oai on Hugging Face, with 241,743 downloads and 40 likes to date. It's a H2OVLChatModel model built for text-generation, 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 requires a quantized checkpoint actually published for this model, check its Hugging Face page before relying on this row.
Cheapest way to run h2ovl-mississippi-800m at its published (BF16) precision: 1× RTX 3070 on simplepod, at $0.050/hr per GPU ($0.050/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.
h2ovl-mississippi-800m: common questions
How much VRAM does h2ovl-mississippi-800m need?
1.8 GB at BF16, 0.9 GB at FP8 (quantized), 0.5 GB at INT4 (quantized). All of those sit under 6 GB, the smallest capacity this page reasons about, so VRAM is not what limits where this model runs. The 1.5 GB of weights plus inference overhead is the whole requirement.
How many copies of h2ovl-mississippi-800m fit on one RTX 3070?
4, by VRAM alone. That card carries 8.0 GB and one copy needs 1.8 GB at BF16, on a live rate of $0.050/hr for the whole card. Throughput is not modelled here, so 4 copies is not 4 times the requests served.
Weight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.
More h2oai models
- h2ovl-mississippi-2b (2.2B, BF16)
- h2o-danube3-500m-chat (514M, BF16)
- bert-base-uncased (110M, F32)
- Qwen3-0.6B (752M, BF16)
- gpt2 (137M, F32)
- Qwen3-8B (8.2B, BF16)
