What GPU do I need to run llava-hf/llava-1.5-13b-hf?
13.4B parameters, published in F16. View on Hugging Face
Set up llava-1.5-13b-hfllava-1.5-13b-hf is published by llava-hf on Hugging Face, with 151,909 downloads and 35 likes to date. It's a LlavaForConditionalGeneration model built for image-text-to-text, published natively in F16.
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.
| Precision | Weight size | Required VRAM | Cheapest live fit | GPUs needed | Est. $/hr (full fit) |
|---|---|---|---|---|---|
| FP16 | 24.9 GB | 29.8 GB | V100 | 1 | $0.187/hr |
| cheaper alt. | V100 | 2 | $0.176/hr | ||
| FP8 (quantized) | 12.4 GB | 14.9 GB | RTX 5060 Ti | 1 | $0.110/hr |
| INT4 (quantized) | 6.2 GB | 7.5 GB | RTX 5060 Ti | 1 | $0.110/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 llava-1.5-13b-hf at its published (F16) precision: 1× V100, at $0.187/hr per GPU ($0.187/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.
llava-1.5-13b-hf: common questions
Does llava-1.5-13b-hf fit on a 32 GB GPU?
Yes. At FP16 it needs 29.8 GB of VRAM, so a 32 GB card holds it with 2.2 GB to spare. A 24 GB card is not enough for it at FP16.
What is the least VRAM llava-1.5-13b-hf can run in?
7.5 GB, at INT4 (quantized), which fits an 8 GB card, against 29.8 GB at FP16. That row assumes an INT4 checkpoint has actually been published for this model, so check its Hugging Face page before planning around it.
Does quantizing llava-1.5-13b-hf lower the GPU bill?
Yes. At FP16 the cheapest live fit is one V100 at $0.187/hr. At FP8 (quantized) it drops to one RTX 5060 Ti at $0.110/hr, provided a quantized checkpoint exists for it.
Weight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.
More LLaVA models
- llava-1.5-7b-hf (7.1B, F16)
- llava-onevision-qwen2-7b-ov (8.0B, BF16)
- LLaVA-Video-7B-Qwen2 (8.0B, BF16)
- llava-v1.6-mistral-7b-hf (7.6B, F16)
- llava-v1.6-mistral-7b (7.6B, BF16)
Related reading: V100 pricing and specs, and The best GPUs for AI, ranked.
