NVIDIA H200 - 141GB usable
Specifications
| Brand | NVIDIA |
|---|---|
| Model | H200 |
| Usable VRAM | 141GB |
| Architecture | Hopper |
| CUDA / Stream Processors | 16,896 |
| Memory Bandwidth | 4800 GB/s |
| TDP | 700W |
| FP32 TFLOPS | 67 |
Current Offers
GPUDojo is reader-supported. When you buy through links on our site, we may earn an affiliate commission.
Price History
Price tracking started: chart will appear after the next snapshot.
For AI / LLM Use
Best for running 70B+ models on a single GPU. Very fast generation speed.
What Models Can It Run?
- 70B full precision
- 70B Q4_K_M, 30B full precision
- 30B Q6_K, 70B Q2_K
- 30B Q4_K_M, 14B full precision, 70B Q2 (tight)
- 14B Q6_K, 30B Q3_K (tight)
- 14B Q4_K_M, 7B full precision
- 7B Q6_K, 14B Q3_K (tight)
- 7B Q4_K_M only
Estimated Performance
Generation: ~360 tokens/sec
Prefill: ~1196 tokens/sec
Recommended Quantisations
- Q6_K or Q8 for best quality
- Q4_K_M for larger models
- Full precision for 30B and below
Pros & Cons
Pros
- 141GB usable VRAM: handles large models
- High memory bandwidth for fast generation
- Hopper architecture: broad CUDA software support
- Consumer card: easy to install, display output
Cons
- 700W TDP: high power draw
Community Verdict
No community reviews yet for the H200. Know a good review? Let us know.