Hy-MT2 models
3 Hy-MT2 models from Tencent on Hugging Face, from 2.0B to 30.1B parameters, published by Tencent in BF16, with a 256K-token context. The smallest official model, Hy-MT2-1.8B, needs about 4.6 GB of VRAM at its published precision; the cheapest live fit is RTX 3070 at $0.088/hr.
Part of the Hunyuan series
Pick a size
One row per official Hy-MT2 size: the VRAM it needs at each precision, the cheapest GPU that holds it today, and the KV cache for a 32K-token context.
| Model | Parameters | Native VRAM | FP8 VRAM | INT4 VRAM | Live GPU fit (native) | Est. $/hr | KV cache at 32K |
|---|---|---|---|---|---|---|---|
| Hy-MT2-1.8B | 2.0B | 4.6 GB | 2.3 GB | 1.1 GB | RTX 3070 | $0.088/hr | 2.0 GB |
| Hy-MT2-7B | 8.0B | 17.9 GB | 9.0 GB | 4.5 GB | RTX A5000 | $0.176/hr | 4.0 GB |
| Hy-MT2-30B-A3B | 30.1B | 67.2 GB | 33.6 GB | 16.8 GB | A100 | $1.31/hr | 3.0 GB |
VRAM is weights times a flat 1.2 overhead; the KV cache is a separate per-model figure at 16-bit, shown where the architecture is published. See the methodology.
Official models (3)
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| Hy-MT2-1.8B | 2.0B | BF16 | 4.6 GB | RTX 3070 | $0.088/hr |
| Hy-MT2-7B | 8.0B | BF16 | 17.9 GB | RTX A5000 | $0.176/hr |
| Hy-MT2-30B-A3B | 30.1B | BF16 | 67.2 GB | A100 | $1.31/hr |
VRAM is for the precision the model is published in: the weights times a flat 1.2 overhead, with the KV cache not included. See the methodology. The fit shown is the lowest-priced single GPU type that holds the model at that precision, or the lowest-priced multi-GPU set (up to 8) when none does.
More from Tencent
- tencent (3 models)
- Hy3 (3 models)
- Hunyuan Instruct (2 models)
- Hy4 (2 models)