Spheron GPU Catalog

NVIDIA B200 GPU: 192GB Blackwell Specs, Pricing & Rental. Rent B200 GPU from $2.68/hr

192GB HBM3e Blackwell with FP4 Transformer Engine. B200 GPU rentals built for trillion-parameter training and 100B+ LLM inference.

At a glance

You can rent an NVIDIA B200 on Spheron starting at $2.68/hr per GPU per hour, the lowest live marketplace rate. Per-minute billing, no contracts, and 8-GPU HGX B200 nodes deploy via NVLink 5.0 with 1.8 TB/s GPU-to-GPU bandwidth. Each B200 ships with 192GB HBM3e, 8 TB/s memory bandwidth, and a 2nd-gen Transformer Engine with native FP4 support, delivering roughly 2x faster LLM training and up to 15x faster inference than H100 at FP4 (per MLPerf). Designed for frontier-scale workloads: 1T+ parameter training, 100B+ parameter inference serving, and multi-modal foundation models where HBM capacity and NVLink bandwidth are the bottleneck.

GPU ArchitectureNVIDIA Blackwell
VRAM192 GB HBM3e
Memory Bandwidth8.0 TB/s

NVIDIA B200 specifications

GPU Architecture
NVIDIA Blackwell
VRAM
192 GB HBM3e
Memory Bandwidth
8.0 TB/s
Tensor Cores
5th Generation
CUDA Cores
20,480
FP64 Performance
40 TFLOPS
FP32 Performance
80 TFLOPS
TF32 Performance
1,125 TFLOPS (dense)
FP8 Performance
4,500 TFLOPS (dense)
FP4 Performance
9,000 TFLOPS (dense)
System RAM
184 GB DDR5
vCPUs
32 vCPUs
Storage
250 GB NVMe Gen5
Network
NVLink 1.8TB/s
TDP
1000W

NVIDIA B200 pricing

ProviderPrice/hrSavings
SpheronYour price
$2.68/hr-
RunPod
$5.89/hr2.2x more expensive
Lambda Labs
$6.08/hr2.3x more expensive
Nebius
$5.50/hr2.1x more expensive
CoreWeave (SXM)
$8.60/hr3.2x more expensive
CoreWeave (NVL)
$10.50/hr3.9x more expensive
AWS (p6-b200)
est. $12.00/hr4.5x more expensive
Custom & Reserved

Need More B200 Than What's Listed?

Reserved Capacity

Commit to a duration, lock in availability and better rates

Custom Clusters

8 to 512+ GPUs, specific hardware, InfiniBand configs on request

Supplier Matchmaking

Spheron sources from its certified data center network, negotiates pricing, handles setup

Need more B200 capacity? Tell us your requirements and we'll source it from our certified data center network.

Typical turnaround: 24–48 hours

When to pick the B200

Scenario 01

Pick B200 if

You're training frontier models (1T+ parameters), serving 100B+ parameter LLMs in production, or running MoE architectures that need the extra HBM capacity and NVLink bandwidth. FP4 support cuts inference cost per token roughly in half vs H100 FP8. If your model already maxes out 80GB on H100, B200 is the direct step up.

Recommended fit
Scenario 02

Pick H100 instead if

Your model fits in 80GB and you want the best price per hour for 70B-class training or inference. H100 is mature, has broad framework support, and costs significantly less per GPU-hour. B200 is overkill for anything under ~100B parameters.

Recommended fit
Scenario 03

Pick H200 instead if

You need 141GB HBM3e to fit larger contexts or KV cache without the full Blackwell price bump. H200 is a drop-in upgrade from H100 and a popular middle ground for serving 70-180B parameter models.

Recommended fit
Scenario 04

Pick B300 or GB200 instead if

You want Blackwell Ultra (B300) with 288GB HBM3e per GPU, or the GB200 Grace-Blackwell Superchip pairing two B200s with a Grace CPU over a 900 GB/s NVLink-C2C link. Both target the largest possible training runs and enterprise-scale reasoning models.

Recommended fit

NVIDIA B200 use cases

Use case / 01
🌐

Trillion-Parameter Model Training

Train the next generation of foundation models at exceptional scale, leveraging 192GB memory and 2nd-gen Transformer Engine.

GPT-4 scale models with 1T+ parametersMulti-modal foundation models (text, image, video, audio)Scientific foundation models for drug discoveryMixture-of-Experts (MoE) architectures at scale
Use case / 02
💬

Advanced LLM Inference

Deploy ultra-large language models for production inference with industry-leading throughput and lowest cost per token.

Real-time inference for 100B+ parameter LLMsMulti-turn conversational AI with long contextRetrieval-augmented generation (RAG) at scaleAgent-based AI systems with reasoning capabilities
Use case / 03

Generative AI at Scale

Power next-generation generative AI applications with support for advanced diffusion models and multi-modal generation.

High-resolution video generation (4K/8K)Real-time 3D asset generation and renderingMusic and audio synthesis modelsCode generation for enterprise applications
Use case / 04
🔬

AI Research & Innovation

Push the boundaries of AI research with frontier-class hardware built for experimental architectures and novel approaches.

Novel neural architecture developmentMulti-agent reinforcement learning at scaleQuantum machine learning simulationsBrain-scale neural network simulation

NVIDIA B200 benchmarks

Llama 2 70B Inference
~12,300 tok/s
FP4, server mode (MLPerf Inference v5.0)
GPT-3 175B Training
~2x faster
vs H100 SXM5 (MLPerf Training)
Llama 3.1 405B Training
~2.2x per-GPU
vs H100 SXM5 (NVIDIA)
FP4 Throughput
~2x vs FP8
2nd-gen Transformer Engine
Memory Capacity
2.4x larger
vs H100 80GB (192GB vs 80GB)
Memory Bandwidth
2.4x faster
vs H100 SXM5 (8.0 vs 3.35 TB/s)

Serve Llama 3.1 405B on 8x B200 with vLLM + FP4

8-GPU HGX B200 node has 1.5TB unified HBM, enough to serve Llama 3.1 405B in FP4 with a 32K+ context window. vLLM enables tensor parallelism across NVLink for low-latency inference.

bash
Spheron
# SSH into your 8x B200 HGX nodessh root@<instance-ip> # NVIDIA PyTorch 24.10+ container has Blackwell + FP4 kernelsdocker run --gpus all --ipc=host --ulimit memlock=-1 \  -p 8000:8000 -v $HOME/.cache:/root/.cache \  nvcr.io/nvidia/pytorch:24.10-py3 bash pip install vllm>=0.6.3 # Launch Llama 3.1 405B with FP4 quantization across 8 GPUsvllm serve meta-llama/Llama-3.1-405B-Instruct \  --tensor-parallel-size 8 \  --quantization fp4 \  --max-model-len 32768 \  --gpu-memory-utilization 0.95 # Test the endpointcurl http://localhost:8000/v1/chat/completions \  -H "Content-Type: application/json" \  -d '{"model":"meta-llama/Llama-3.1-405B-Instruct","messages":[{"role":"user","content":"Hello"}]}'

On an 8x B200 node, expect 5-8x higher tokens/sec than an 8x H100 node at FP4 thanks to the 2nd-gen Transformer Engine and NVLink 5.0.

Interconnect fabric

NVLink Switch Configuration

B200 GPUs feature the latest NVLink switch technology providing 1.8 TB/s bidirectional bandwidth per GPU. This enables near-linear scaling for multi-GPU training of trillion-parameter models with minimal communication overhead.

01NVLink 5.0 with 1.8 TB/s per GPU bandwidth
0218x bandwidth improvement over PCIe Gen5
03Full NVSwitch connectivity for 8-GPU systems
04Unified memory addressing across all GPUs
05Direct GPU-to-GPU communication without CPU
06Support for NVIDIA SHARP for in-network computing
07Optimized for DeepSpeed ZeRO-3 and FSDP
08Sub-100ns GPU-to-GPU latency
Scale

Need a custom multi-node cluster or reserved capacity?

B200 vs alternatives

NVIDIA B200 guides and resources

01Technical Brief

NVIDIA B200 Release Date and Cloud Availability

The NVIDIA B200 GPU was announced at GTC March 2024 as the flagship of the new Blackwell architecture. The first production HGX B200 systems shipped in late 2024, with broad GPU cloud availability rolling out through H1 2025. CoreWeave was first to GA on HGX B200 in October 2024; Nebius, Lambda Labs, and RunPod followed in Q1 2025; AWS p6-b200 reached general availability in mid-2025, with Azure ND B200 v6 and Google Cloud A4 close behind.

On Spheron the B200 SXM6 is available with per-minute billing and no contract. Spot pricing is meaningfully below the dedicated rate for fault-tolerant workloads. Live capacity and current pricing is on the pricing page. The B300 Blackwell Ultra (288GB HBM3e at 10 TB/s) is the next step up for workloads that exceed B200's 192GB VRAM ceiling; the GB200 NVL72 rack-scale system pairs 72 B200 GPUs into a unified memory domain for frontier pre-training.

02Technical Brief

B200 VRAM and Memory Bandwidth: 192GB HBM3e at 8 TB/s

The B200 ships with 192GB of HBM3e memory at 8 TB/s of bandwidth. That is 1.36x the VRAM and roughly 1.67x the bandwidth of the H200 (141GB HBM3e at 4.8 TB/s), and 2.4x the VRAM at 2.39x the bandwidth of the H100 (80GB HBM3 at 3.35 TB/s). For autoregressive LLM decode at batch size 1, the B200's bandwidth ceiling for a 70B FP16 model is roughly 57 tokens per second, more than double the H100.

Where the 192GB VRAM matters: a Llama 405B model fits in FP4 on a single B200, a 200B-class model fits in FP8 with KV cache headroom for production batches, and trillion-parameter MoE models fit across an 8-GPU HGX B200 node with 1.5TB of pooled HBM. The second-generation Transformer Engine adds native FP4 support, roughly doubling effective throughput on inference workloads that tolerate the precision reduction. For workloads that exceed 192GB VRAM, the B300 (288GB HBM3e) is the next step.

FAQ / 11

NVIDIA B200 FAQ

NVIDIA B200 alternatives and related GPUs