What GPU do I need to run fdtn-ai/antares-1b?
1.8B parameters, published in BF16. View on Hugging FaceGated
antares-1b is published by fdtn-ai on Hugging Face, with 14,867 downloads and 291 likes to date. It's a GraniteMoeHybridForCausalLM model built for text-generation, published natively in BF16, and gated: you'll need to accept the model's terms on Hugging Face before downloading weights.
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 antares-1b at its published (BF16) precision: 1× RTX 3070 on simplepod, at $0.050/hr per GPU ($0.050/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 fdtn-ai models
- Foundation-Sec-1.1-8B-Instruct (8.0B, BF16)
- Foundation-Sec-8B-Instruct (8.0B, BF16)
- Foundation-Sec-8B-Reasoning (8.0B, BF16)
- Qwen3-0.6B (752M, BF16)
- gpt2 (137M, F32)
- Qwen3-8B (8.2B, BF16)
