What GPU do I need to run tencent/Hy3-FP8?
298.8B parameters, published in F8_E4M3. View on Hugging Face
Hy3-FP8 is published by tencent on Hugging Face, with 40,013 downloads and 70 likes to date. It's a HYV3ForCausalLM model built for text-generation, published natively in F8_E4M3.
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 Hy3-FP8 at its published (F8_E4M3) precision: 7× L40 on massecompute, at $0.772/hr per GPU ($5.41/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 tencent models
- HunyuanOCR (1.1B, BF16)
- Hy3-preview (298.8B, BF16)
- Hunyuan-A13B-Instruct (80.4B, BF16)
- Hy-MT2-1.8B (2.0B, BF16)
- Hy-MT2-30B-A3B (30.1B, BF16)
- Hunyuan-7B-Instruct (7.5B, BF16)
