Key Specifications
We couldn't find any available H800 GPUs. Search for alternative GPUs.
Frequently Asked Questions
Why choose the H800?
80GB HBM3 with FP8 Transformer Engine, similar compute to H100. Available in the Chinese market where H100 is restricted. 400 GB/s NVLink still supports multi-GPU training.
When is the H800 not a good fit?
Reduced NVLink bandwidth (400 vs 900 GB/s) compared to H100. Not ideal for communication-heavy distributed training across many nodes. Outside China, the H100 is typically a better choice.
What size AI models can the H800 run?
With 80GB of VRAM, the H800 is well suited to 30B-class models in FP16, and 70B-class models in 4-bit or 8-bit quantized form.
How much VRAM does the H800 have?
The H800 has 80GB of VRAM. Multi-GPU setups increase total memory, but that memory is not automatically pooled across GPUs.
What is the H800's memory bandwidth?
The H800 has 2,000 GB/s of memory bandwidth. Higher bandwidth helps with faster data transfer between GPU memory and compute cores.
What data types does the H800 support?
The H800 supports 7 precision formats. Training: BF16, FP16, TF32, FP32. Inference: FP8, INT8. Scientific: FP64.
Does the H800 support NVLink?
Yes. The H800 supports NVLink with 400 GB/s of bidirectional bandwidth. This helps accelerate multi-GPU communication.
Technical Specifications
| H800 PCIe | H800 NVL | |
|---|---|---|
| Architecture | NVIDIA Hopper | NVIDIA Hopper |
| CUDA Cores | 18,432 | 18,432 |
| Tensor Cores | 528 (4th Generation) | 528 (4th Generation) |
| GPU Memory | 80GB HBM2e | 94GB HBM3 |
| Memory Bandwidth | 2 TB/s | 3.9 TB/s |
| ECC | Yes | Yes |
| FP32 | 51 TFLOPS | 51 TFLOPS |
| TF32 Tensor Core | 756 TFLOPS | 756 TFLOPS |
| FP16 Tensor Core | 1,513 TFLOPS | 1,513 TFLOPS |
| FP8 Tensor Core | 3,026 TFLOPS | 3,026 TFLOPS |
| System Interface | PCIe Gen5 x16 | PCIe Gen5 x16 |
| NVLink | 400 GB/s | 400 GB/s |
| Max TDP | 350W | 400W |
| Multi-Instance GPUs | Up to 7 MIGs | Up to 7 MIGs |
| Form Factor | PCIe, dual-slot | PCIe, dual-slot |
Alternatives to Nvidia H800
Last updated