What GPU do I need to run LightOriginsHQ/LightNav-0?
4.8B parameters, published in BF16. View on Hugging Face
Set up LightNav-0LightNav-0 is published by LightOriginsHQ on Hugging Face, with 26 downloads and 17 likes to date. It's a Qwen3VLForConditionalGeneration model built for robotics, 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.
| Precision | Weight size | Required VRAM | Cheapest live fit | GPUs needed | Est. $/hr (full fit) |
|---|---|---|---|---|---|
| BF16 | 9.0 GB | 10.8 GB | RTX 5060 Ti | 1 | $0.110/hr |
| FP8 (quantized) | 4.5 GB | 5.4 GB | RTX 5060 Ti | 1 | $0.110/hr |
| INT4 (quantized) | 2.3 GB | 2.7 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 LightNav-0 at its published (BF16) precision: 1× RTX 5060 Ti, at $0.110/hr per GPU ($0.110/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.
LightNav-0: common questions
Does LightNav-0 fit on a 12 GB GPU?
Yes. At BF16 it needs 10.8 GB of VRAM, so a 12 GB card holds it with 1.2 GB to spare. An 8 GB card is not enough for it at BF16.
What is the least VRAM LightNav-0 can run in?
2.7 GB, at INT4 (quantized), which fits a 6 GB card, against 10.8 GB at BF16. That row assumes an INT4 checkpoint has actually been published for this model, so check its Hugging Face page before planning around it.
Weight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.
More Qwen3 models
- Qwen3-VL-4B-Instruct-FP8 (4.8B, F8_E4M3)
- Qwen3-VL-4B-Instruct (4.4B, BF16)
- Qwen3-VL-Embedding-8B (8.1B, BF16)
- Qwen3-VL-8B-Instruct (8.8B, BF16)
- qwen3vl-resume-parser (8.8B, BF16)
Related reading: H100 pricing and specs, The best GPUs for AI, ranked, and Best GPU for LLM inference.
