Hy3-FP8: GPU memory and hosting cost
Open weights · 298.79 billion parameters · Mixture of experts · 262,144-token context · licence apache-2.0
No cloud sells this model per token: to use it you run it yourself, on GPU instances you rent.
Run it yourself
It needs 373.5 GB of GPU memory at fp8, the precision it ships in.
| Cloud | Cheapest instance that fits | GPUs | An hour | A month, around the clock |
|---|---|---|---|---|
| AWS | p4de.24xlarge | 8 × A100 80 GB | $27.45 | $20,036 |
| Alibaba Cloud | ecs.gn8v-4x.8xlarge | 4 × GPU H 96 GB | $29.25 | $21,349 |
| Azure | Standard_ND96amsr_A100_v4 | 8 × A100 80 GB | $32.77 | $23,922 |
| Google Cloud | a2-ultragpu-8g | 8 × A100 80 GB | $40.55 | $29,602 |
More from Tencent
Similar size, open weights
- Llama 4 Maverick 17B
- Llama 3.1 405B
- Qwen3 235B A22B
- GLM-5.3-Flash
- DeepSeek-V4-Flash-0731
- DeepSeek-V4-Flash
List prices collected 5 October 2026, refreshed every three hours. No negotiated rates or taxes.