What GPU do I need to run qihoo360/fg-clip-base?
150M parameters, published in F32. View on Hugging Face
fg-clip-base is published by qihoo360 on Hugging Face, with 18,627 downloads and 10 likes to date. It's a FGCLIPModel model built for zero-shot-image-classification, published natively in F32.
VRAM required & cheapest live GPU fit
Required VRAM = weight size at each precision times a flat 1.2 overhead for activations and fragmentation. The KV-cache grows with context and is not in that factor; it is listed per model below where the architecture is published. Full formula and assumptions: methodology.
| Precision | Weight size | Required VRAM | Cheapest live fit | GPUs needed | Est. $/hr (full fit) |
|---|---|---|---|---|---|
| FP32 | 0.6 GB | 0.7 GB | RTX 3070 | 1 | $0.088/hr |
| FP8 (quantized) | 0.1 GB | 0.2 GB | RTX 4070 | 1 | $0.154/hr |
| INT4 (quantized) | 0.1 GB | 0.1 GB | RTX 3070 | 1 | $0.088/hr |
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 fg-clip-base at its published (F32) precision: 1× RTX 3070, at $0.088/hr per GPU ($0.088/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.
fg-clip-base: common questions
How much VRAM does fg-clip-base need?
0.7 GB at FP32, 0.2 GB at FP8 (quantized), 0.1 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 0.6 GB of weights plus inference overhead is the whole requirement.
Can fg-clip-base run in 16-bit instead of FP32?
Yes. Its published weights are FP32, 0.6 GB, or 0.7 GB once inference overhead is added. Loading the same weights in 16 bits halves that to 0.3 GB, or 0.3 GB with overhead. How much accuracy the cast costs is model-specific and is not measured here.
How many copies of fg-clip-base fit on one RTX 3070?
11, by VRAM alone. That card carries 8.0 GB and one copy needs 0.7 GB at FP32, on a live rate of $0.088/hr for the whole card. Throughput is not modelled here, so 11 copies is not 11 times the requests served.
Weight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.
More on fg-clip-base
Fits on an 8 GB GPU at FP32: every model that fits in 8 GB.
Related reading: RTX 3070 pricing and specs, How much VRAM you need for LLMs, and What AI inference is.
Your own GPU cloud accounts
One console for the GPU clouds you already rent from. Your keys stay on your machine.
$20 a month, flat