What GPU do I need to run poolside/Laguna-XS.2?
33.4B parameters, published in BF16. View on Hugging Face
Laguna-XS.2 is published by poolside on Hugging Face, with 33,115 downloads and 320 likes to date. It's a LagunaForCausalLM 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 caveat: requires a quantized checkpoint actually published for this model, check its Hugging Face page before relying on this row.
Cheapest way to run Laguna-XS.2 at its published (BF16) precision: 1× A100 on runpod, at $1.19/hr per GPU ($1.19/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 poolside models
- Laguna-S-2.1-FP8 (117.6B, F8_E4M3)
- Laguna-XS-2.1 (33.4B, BF16)
- Laguna-S-2.1 (117.6B, BF16)
- Qwen3-0.6B (752M, BF16)
- gpt2 (137M, F32)
- Qwen3-8B (8.2B, BF16)
