What GPU do I need to run OBLITERATUS/Gemma-4-12B-OBLITERATED?
12.0B parameters, published in BF16. View on Hugging Face
Gemma-4-12B-OBLITERATED is published by OBLITERATUS on Hugging Face, with 26,498 downloads and 440 likes to date. It's a Gemma4UnifiedForConditionalGeneration 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 Gemma-4-12B-OBLITERATED at its published (BF16) precision: 1× RTX 4080 Super on simplepod, at $0.380/hr per GPU ($0.380/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 OBLITERATUS models
- Qwen3.8-27B-OBLITERATED (27.8B, BF16)
- gemma-4-E4B-it-OBLITERATED (8.0B, F16)
- Ornith-1.5-9B-OBLITERATED (9.7B, BF16)
- Qwen3-0.6B (752M, BF16)
- gpt2 (137M, F32)
- Qwen3-8B (8.2B, BF16)
