Skip to main content

NVIDIA B100 (Blackwell)

Product Overview

The NVIDIA B100, released in 2024, is the entry-level data center GPU of the Blackwell architecture. It uses a dual-die design interconnected via a 10 TB/s NV-HBI internal bridge. With a relatively modest 700W TDP, the B100 can drop directly into existing H100/H200 server baseboards, making it a top choice for cloud providers deploying Blackwell at scale.

Important: The B100 was largely surpassed by the B200 in actual 2024–2025 deployments. Many cloud providers (e.g., Modal, CoreWeave) skipped the B100 entirely.

Core Specifications

ParameterValue
ArchitectureBlackwell GB100
Process NodeTSMC 4NP
Transistor Count208 billion (dual-die)
Memory192 GB HBM3e
Memory Bandwidth8 TB/s
FP4 Tensor Core14 PFLOPS (sparse)
FP6 Tensor Core~9.3 PFLOPS (sparse, estimated)
FP8 Tensor Core7 PFLOPS (sparse)
FP16 Tensor Core3.5 PFLOPS (sparse)
FP64 Tensor Core30 TFLOPS
NVLink1.8 TB/s (5th Gen)
TDP700 W
PCIeGen 5
Form FactorSXM

B100 vs B200 Key Differences

MetricB100B200Advantage
TDP700 W1,000 WB100 lower
FP4 Compute14 PFLOPS18 PFLOPSB200 +28%
FP8 Compute7 PFLOPS9 PFLOPSB200 +28%
Memory192 GB HBM3e192 GB HBM3eSame
Memory Bandwidth8 TB/s8 TB/sSame
Server Compat.Fits H100/H200 baseboardRequires new serverB100 more flexible
Price (Reference)N/A$5.87/hr (cloud)

Vendor Information

ParameterValue
ManufacturerNVIDIA Corporation
Official Websitehttps://www.nvidia.com
Product Pagehttps://www.nvidia.com/en-us/data-center/blackwell/
Architecture CodenameUmbriel (internal)

Software & Drivers

Key Features

  • 5th Gen Tensor Cores: Native FP4 / FP6 precision support
  • 2nd Gen Transformer Engine: Automatic FP4 precision conversion
  • NVLink 5.0: 1.8 TB/s GPU-to-GPU interconnect
  • RAS Engine: Reliability, Availability, Serviceability
  • Confidential Computing: Hardware-level TEE support

Use Cases

  • LLM training and inference
  • MoE (Mixture of Experts) models
  • Recommendation systems
  • Incremental upgrade of existing H100 clusters