Rent NVIDIA B200 GPUs by the minute.
Training and inference at scale. 180 GB per GPU, billed by the minute.
BlackwellDatacenter
B200
Training and inference at scale
- VRAM
- 180 GB
- From
- $9.35/h
Israel
United States
GPU Cloud · Secure
B200 rates per GPU-hour.
| GPU | VRAM | Countries | On demand | SpotInterruptible |
|---|---|---|---|---|
| B200 | 180 GB |
| from $9.35/h | Not in stock |
Prices on Nov 14, 2026, 20:35 UTC. US dollars, per GPU, before tax.
Community machines. Priced by their owners, per hour. Each rate in the console.Explore Community
The B200, in numbers.
- Architecture
- NVIDIA Blackwell
- GPU memory
- 180 GB per GPUHBM3e
- Memory bandwidth
- 8 TB/s
- Interconnect
- NVLink 5 · 1.8 TB/s
- Form factor
- B200
- Image
- Ubuntu 24.04 LTS, NVIDIA driver 570, CUDA 12.8
- Billing
- By the minute
What fits in 180 GB.
Open models on one B200, or split across up to 8.
| Model | 16-bit | 4-bit |
|---|---|---|
| Llama 3.1 8B Instruct | 1 GPUNeeds 19.5 GiB | 1 GPUNeeds 6.1 GiB |
| Mistral 7B Instruct v0.3 | 1 GPUNeeds 17.8 GiB | 1 GPUNeeds 5.7 GiB |
| Gemma 2 27B IT | 1 GPUNeeds 63.5 GiB | 1 GPUNeeds 17.9 GiB |
| Qwen2.5 32B Instruct | 1 GPUNeeds 74.8 GiB | 1 GPUNeeds 20.4 GiB |
| Mixtral 8x7B Instruct | 1 GPUNeeds 106.0 GiB | 1 GPUNeeds 27.7 GiB |
| Llama 3.3 70B Instruct | 1 GPUNeeds 160.3 GiB | 1 GPUNeeds 42.0 GiB |
| Qwen2.5 72B Instruct | 1 GPUNeeds 165.0 GiB | 1 GPUNeeds 43.1 GiB |
| FLUX.1 [dev] | 1 GPUNeeds 38.9 GiB | 1 GPUNeeds 10.5 GiB |
| Whisper large-v3 | 1 GPUNeeds 4.5 GiB | 1 GPUNeeds 1.9 GiB |
Estimated by the GPU calculator for a 4,096-token context and one request: weights, KV cache and runtime overhead. Launch by workload
What runs well on the B200.
- Fine-tuningTrain on your data. Keep the weights.
- LLM inferenceAn OpenAI-compatible endpoint with vLLM.
- Batch jobsThousands of files, one session.
- RecipesLoRA fine-tuningFine-tune an open-weight LLM with LoRA or QLoRA using the Hugging Face TRL CLI on a Node Lodge GPU, then copy the adapter off the machine.
- RecipesvLLMServe an open-weight LLM with vLLM on a Node Lodge machine. Install with uv, start the OpenAI-compatible server, query it through an SSH tunnel.
Next to the B200.
About the B200.
- How much does an NVIDIA B200 cost per hour?
- From $9.35 per GPU-hour on demand on Nov 14, 2026, 20:35 UTC, in US dollars before tax. Billed per minute from prepaid credit, with no minimum.
- How much memory does the B200 have?
- 180 GB of HBM3e per GPU. Memory bandwidth: 8 TB/s.
- Where are B200 GPUs located?
- Countries: Israel and United States. In partner datacenters, under Node Lodge Secure. The console shows the city of each machine.
- Which models run on one B200?
- At 16-bit: Llama 3.1 8B Instruct, Mistral 7B Instruct v0.3, Gemma 2 27B IT, Qwen2.5 32B Instruct, Mixtral 8x7B Instruct, Llama 3.3 70B Instruct, Qwen2.5 72B Instruct, FLUX.1 [dev], and Whisper large-v3. At 4-bit: Llama 3.1 8B Instruct, Mistral 7B Instruct v0.3, Gemma 2 27B IT, Qwen2.5 32B Instruct, Mixtral 8x7B Instruct, Llama 3.3 70B Instruct, Qwen2.5 72B Instruct, FLUX.1 [dev], and Whisper large-v3. Size any other model with the GPU calculator.
Request access.
Tell us what you will run. Your access arrives by email.