B200
The B200 is a cloud GPU with 180 GB of memory and 1000 W TDP. It is currently available from 4 providers starting at $5.31/hr, with a market median of $7.15/hr across 29 offerings.
Best deal
Hardware specifications
- Architecture
- Blackwell
- VRAM
- 180 GB
- Memory type
- HBM3
- Memory bandwidth
- 8,000 GB/s
- FP16
- 2250 TFLOPS
- FP32
- 75 TFLOPS
- TDP
- 1000 W
Same across all providers.
Market comparison
All-time price history
Offerings
LLMs that fit
| Model | Params | 16-bit | 8-bit | 4-bit |
|---|---|---|---|---|
DeepSeek V4 Pro DeepSeek | 1.6T 49B active | Not released | Not released | Barely fits on 7× |
Kimi K2.5 Moonshot AI | 1T 32B active | Not released | Not released | Barely fits on 5× |
GLM-5.2 Z.ai | 753B | Needs >8 GPUs | Barely fits on 7× | Barely fits on 4× |
DeepSeek R1 DeepSeek | 671B 37B active | Not released | Barely fits on 6× | 4× · 142.8 GB free |
DeepSeek V4 Flash DeepSeek | 284B | Not released | Not released | 2× · 129.6 GB free |
Solar Open2 250B Upstage | 250B 15B active | 5× · 178.8 GB free | 3× · 144 GB free | 2× · 129.6 GB free |
Qwen3 235B-A22B Alibaba | 235B 22B active | Barely fits on 4× | 3× · 168 GB free | 2× · 142.8 GB free |
Laguna-S 2.1 Poolside | 118B 8B active | Barely fits on 2× | 2× · 174 GB free | 1× · 72 GB free |
gpt-oss-120b OpenAI | 117B 5.1B active | Not released | Not released | 1× · 86.4 GB free |
Llama 3.1 70B Meta | 70B | Barely fits on 1× | 1× · 88.2 GB free | 1× · 126 GB free |
Qwen3.6 35B-A3B Alibaba | 35B 3B active | 1× · 76.8 GB free | 1× · 123.6 GB free | 1× · 146.4 GB free |
Qwen3 32B Alibaba | 32.8B | 1× · 85.2 GB free | 1× · 128.4 GB free | 1× · 150 GB free |
Estimates: model weights plus 20% for KV cache and runtime overhead, at short context lengths. Long contexts and large batches need more. Rows marked “tight” hold the weights but not that full margin. A ×N figure is the total VRAM across N of these GPUs and makes no claim about interconnect throughput.
Similar GPUs
See more GPUs like this in
Frequently asked questions
How much does the B200 cost per hour?
The cheapest B200 offering starts at $5.31/hr, and the market median is $7.15/hr.
Which cloud providers offer the B200?
We track B200 offerings from HardwareHQ, Vast.ai.
How much VRAM does the B200 have?
The B200 has 180 GB of VRAM.
What LLMs can run on the B200?
With 180 GB of VRAM, the B200 can run 16 of our tracked models in 4-bit quantization, including DeepSeek V4 Pro, Kimi K2.5, GLM-5.2. 10 models fit in 16-bit precision.
What's the biggest LLM I can run on multiple B200s?
With 8× B200 (1440 GB total), the largest tracked model that fits in 16-bit is Solar Open2 250B (250B params), which needs 5× GPUs.
Where is the B200 cheapest?
The cheapest B200 offering in our catalog is HardwareHQ at $5.98/hr per GPU-hour (×8).