What GPU do I need to run HuggingFaceTB/SmolVLM2-500M-Video-Instruct?
507M parameters, published in F32. View on Hugging Face
SmolVLM2-500M-Video-Instruct is published by HuggingFaceTB on Hugging Face, with 1,506,612 downloads and 171 likes to date. It's a SmolVLMForConditionalGeneration model built for image-text-to-text, published natively in F32.
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 SmolVLM2-500M-Video-Instruct at its published (F32) precision: 1× P4 on akash, at $0.032/hr per GPU ($0.032/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 HuggingFaceTB models
- SmolLM2-135M (135M, BF16)
- SmolLM2-135M-Instruct (135M, BF16)
- SmolLM3-3B (3.1B, BF16)
- SmolLM2-360M-Instruct (362M, BF16)
- SmolLM3-3B-Base (3.1B, BF16)
- SmolLM2-360M (362M, BF16)
