RTX 4080 クラウド GPU レンタル $0.2335/時間から | NovaPod
市場 最低 $0.2335/時間
中央値 —/時間 · p10 —/時間
オファーが1件あります
最小 $0.1190
平均 $0.2456
最大 $1.7486
最小 $0.0902
平均 $0.1530
最大 $1.7486 仕様 The Nvidia RTX 4080 is a high-performance graphics card designed for gamers and creators, offering exceptional speed, advanced ray tracing, and AI-enhanced graphics.
GPU Name AD103
Architecture Ada Lovelace
CUDA Cores / GPU 9728
CUDA Cores / SM 128
Die Size 378.6 mm2
Frame Buffer Memory Size and Type 16 GB GDDR6X
GPCs 7
GPU Boost Clock (MHz) 2505
GPU Codename AD103
L1 Data Cache/Shared Memory 9728 KB
L2 Cache Size ← すべての GPU
NovaPod © 2026 NovaPod Technologies Ltd.
NovaPod AI コンピュートプラットフォーム · ライブのオンデマンド GPU クラスタ、Docker Pod、秒単位の暗号資産請求。サポート: support@novapod.io
1.75 0.09
65536 KB
Manufacturing Process TSMC 4N NVIDIA Custom Process
Memory Bandwidth 716.8 GB/sec
Memory Clock (Data Rate) 22.4 Gbps
PCI Express Interface Gen 4
Peak BF16 TFLOPS (non-Tensor) 48.7
Peak BF16 Tensor TFLOPS with FP32 Accumulate 97.5/1952
Peak FP16 TFLOPS (non-Tensor) 48.7
Peak FP16 Tensor TFLOPS with FP16 Accumulate 194.9/389.82
Peak FP16 Tensor TFLOPS with FP32 Accumulate 97.5/1952
Peak FP32 TFLOPS (non-Tensor) 48.7
Peak FP8 Tensor TFLOPS with FP16 Accumulate 389.9/779.82
Peak FP8 Tensor TFLOPS with FP32 Accumulate 389.9/779.82
Peak INT32 TOPS (non-Tensor) 24.4
Peak INT4 Tensor TOPS 779.8/1559.62
Peak INT8 Tensor TOPS 389.9/779.822
Peak TF32 Tensor TFLOPS 48.7/97.42
Pixel Fill-rate (Gigapixels/sec) 280.6
Register File Size 19456 KB
TGP (Total Graphics Power) 320 W
Tensor Cores / GPU 304 (4th Gen)
Tensor Cores / SM 4 (4th Gen)
Texel Fill-rate (Gigatexels/sec) 761.5
Transistor Count 45.9 Billion
Video Engines 2 x NVENC (8th Gen), 1 x NVDEC (5th Gen)