← All GPUs
H100 SXM
NVIDIA · Data Center GPU · 2023
Performance Benchmarks
Image Generation all sourced rows →
| Model | Metric | Value | Source |
|---|---|---|---|
| SDXL Turbo FP16 | images per minute |
200
img/min
ComfyUI · 2025-06-01
|
Manufacturer benchmark NVIDIA Official Specs ↗ |
LLM Inference all sourced rows →
| Model | Metric | Value | Source |
|---|---|---|---|
|
Llama-3-70B
Q4 80GB HBM3 — editorial estimate pending article-level source verification |
tokens per second |
90
tok/s
est llama.cpp · 2025-06-01
|
Estimated MLPerf Inference Results ↗ |
|
Llama-3-8B
Q4 80GB HBM3 — editorial estimate pending article-level source verification |
tokens per second |
500
tok/s
est llama.cpp · 2025-06-01
|
Estimated NVIDIA Official Specs ↗ |
Full Specifications
Vram gb
80 GB
Vram type
HBM3
Memory bandwidth gbps
3350 GB/s
Tdp watts
700 W
Cuda cores
16896
Architecture
Hopper
Fp8 tflops
3958 TFLOPS
Related GPUs
Guides & Tools
CompareAIHardware.com participates in the Amazon Associates program. As an Amazon Associate, we earn from qualifying purchases.