Blackwell
Blackwell is a GPU microarchitecture introduced by NVIDIA, targeting high-performance computing, artificial intelligence training, and inference applications. The architecture improves computational throughput and energy efficiency relative to its predecessor, supports large-scale parallel computing tasks, and incorporates optimizations specific to AI workloads such as large language models. The Blackwell architecture is deployed across multiple NVIDIA GPU product lines serving data center and professional computing domains.
Core Facts
NVFP4 is a 4-bit floating-point (FP4) quantization format introduced by NVIDIA, designed specifically for the hardware acceleration capabilities of Blackwell architecture GPUs
NVIDIA's H100/H200 series GPUs hold more than 80% of the AI training and inference market.
The RTX 5090 has 32 GB of VRAM.
Timeline (last 90 days)
FP8 is natively supported on Hopper and Blackwell architecture GPUs (H100, H200, B200, B300), but the A100 has no FP8 hardware support.
Argonne National Laboratory will deploy Solstice, a system built in cooperation with Oracle, equipped with 100,000 Blackwell GPUs, mainly targeting emerging AI workloads and running at 16-bit, 8-bit, and even 4-bit precision.
The Blackwell architecture only went into mass production in 2025, and many mainstream tutorials and pre-compiled packages are still built for the Ampere or Ada Lovelace architectures.
The RTX 5090 belongs to the Blackwell architecture, and during deployment the CUDA, PyTorch, and compiled package versions must be strictly matched; otherwise, Attention-related dependencies that accelerate inference are prone to errors.
GB202 is the highest-specification flagship GPU die under NVIDIA's Blackwell architecture.
NVIDIA RTX Spark is a discrete GPU platform for ultra-thin laptops, based on the Blackwell architecture, focused on local AI inference and optimized for INT4/FP8 quantized inference tasks.
The RTX 5090 is the consumer flagship graphics card under NVIDIA's Blackwell architecture.
The Yoga Pro 9N is built on the RTX Spark platform, combining a CPU with up to 20 cores and an RTX graphics card based on the Blackwell architecture.
FlashAttention-4 on the NVIDIA Blackwell architecture exposed the imbalance of special function units within the attention mechanism.
The RTX 5090 features a Blackwell architecture GPU with extremely high FP8/FP16 floating-point compute performance, which can theoretically be used for large-scale AI model training and inference.
40 more timeline events
All Facts (20)
NVFP4 is a 4-bit floating-point (FP4) quantization format introduced by NVIDIA, designed specifically for the hardware acceleration capabilities of Blackwell architecture GPUs
90%VerifiedNVIDIA's H100/H200 series GPUs hold more than 80% of the AI training and inference market.
90%VerifiedThe RTX 5090 has 32 GB of VRAM.
80%VerifiedCore innovations of the Blackwell architecture include the second-generation Transformer Engine (supporting FP4 precision), the NVLink Switch system (supporting interconnection of 576 GPUs), 20 petaFLOPS of FP4 compute, and 192 GB HBM3e memory (with bandwidth reaching 8 TB/s).
80%VerifiedBlackwell's second-generation Transformer Engine adds FP4 precision support, which in theory can improve Transformer model training throughput by 2–4x compared to the H100.
75%VerifiedNVIDIA designed a dedicated Tensor Core instruction mma.kind::mxf4 for NVFP4 in the Blackwell architecture (SM 100/103, such as the B100 and B200 series), and adopted an FP8 scaling factor mechanism with one scale per group of 16 elements.
75%VerifiedNVIDIA Blackwell 架构于2024年发布，是继 Hopper（H100）之后的新一代数据中心 GPU 架构
75%VerifiedThe NVIDIA Blackwell architecture (GB200/B200 series) introduces native FP4 tensor cores at the hardware level
75%VerifiedBlackwell (B100/B200 series) was released in 2024, manufactured using TSMC's 4NP process, with a single GPU integrating 208 billion transistors
75%VerifiedThe NVIDIA RTX 5090 is based on the Blackwell architecture, is equipped with 32 GB of GDDR7 memory, and has a theoretical FP16 computing power exceeding 100 TFLOPS.
70%VerifiedThe RTX 5070 belongs to NVIDIA's Blackwell architecture consumer graphics card product line and features approximately 12 GB of VRAM.
65%VerifiedThe RTX 5090 is based on the Blackwell architecture, equipped with 32 GB GDDR7 memory with a bandwidth of 1.79 TB/s, a significant leap compared to the RTX 4090's 1 TB/s.
65%VerifiedThe RTX 5090 is based on NVIDIA's Blackwell architecture.
65%VerifiedThe RTX 5090 is based on NVIDIA's Blackwell architecture.
65%VerifiedThe GB300 is NVIDIA's flagship data center chip in the Blackwell Ultra series, integrating HBM3e memory with a single-card capacity of 288 GB.
65%VerifiedThe Blackwell architecture is named after American mathematician and statistician David Blackwell.
65%UnverifiedGB200中的'G'代表Grace CPU，'B'代表Blackwell GPU
95%Unverified2024年GTC上发布了Blackwell架构GPU和NIM（NVIDIA Inference Microservices）等产品
90%Unverified每颗Blackwell GPU拥有高达192GB HBM3e显存
90%Unverified同一组编译选项在 Ampere、Hopper、Blackwell 等不同 GPU 架构上的表现可能截然不同
90%