Chutes
Node Growth Analytics
GPU node growth patterns over the last 30 days
GPU Node Counts
Below are the current counts of GPU nodes on the Chutes platform, with various statistics on the GPUs themselves, and summaries of the total compute currently available.
GPU Node Table
Below are the current counts of GPU nodes on the Chutes platform, with various statistics on the GPUs themselves, and summaries of the total compute currently available.
| GPU Name | Provisioned | Memory | CUDA Cores | Memory Bandwidth | FP32 Performance | Max Power |
|---|---|---|---|---|---|---|
| NVIDIA H200 141GB SXM | 631 | 141 GB HBM3e | 16,896 | 4.8 TB/s | 67 TFLOPS | 700 W |
| 123 | N/A | N/A | N/A | N/A | N/A | |
| NVIDIA RTX A6000 | 11 | 48 GB GDDR6 (ECC) | 10,752 | 768 GB/s | 38.7 TFLOPS | 300 W |
| NVIDIA A100 80GB SXM | 6 | 80 GB HBM2e | 6,912 | 2.039 TB/s | 19.5 TFLOPS | 400 W |
| 3 | N/A | N/A | N/A | N/A | N/A | |
| NVIDIA GeForce RTX 3090 | 2 | 24 GB GDDR6X | 10,496 | 936 GB/s | ~35.7 TFLOPS | 350 W |
| NVIDIA H100 80GB SXM | 2 | 80 GB HBM3 | 16,896 | 3.35 TB/s | 67 TFLOPS | 700 W |
| NVIDIA GeForce RTX 4090 | 1 | 24 GB GDDR6X | 16,384 | 1008 GB/s | ~83 TFLOPS | 450 W |
| NVIDIA A100 80GB PCIe | 0 | 80 GB HBM2e | 6,912 | 1.935 TB/s | 19.5 TFLOPS | 300 W |
| NVIDIA A100 40GB PCIe | 0 | 40 GB HBM2 | 6,912 | 1.6 TB/s | 19.5 TFLOPS | 250 W |
| NVIDIA A100 40GB SXM | 0 | 40 GB HBM2 | 6,912 | 1.6 TB/s | 19.5 TFLOPS | 400 W |
| NVIDIA A40 | 0 | 48 GB GDDR6 (ECC) | 10,752 | 696 GB/s | 37.4 TFLOPS | 300 W |
| NVIDIA RTX A4000 | 0 | 16 GB GDDR6 (ECC) | 6,144 | 448 GB/s | 19.2 TFLOPS | 140 W |
| NVIDIA RTX A5000 | 0 | 24 GB GDDR6 (ECC) | 8,192 | 768 GB/s | 27.8 TFLOPS | 230 W |
| NVIDIA RTX 6000 Ada Generation | 0 | 48 GB GDDR6 (ECC) | 18,176 | 960 GB/s | 91.1 TFLOPS | 300 W |
| NVIDIA B200 Blackwell | 0 | 192 GB HBM3E | 18,000 | 8 TB/s | 160 TFLOPS | 700 W |
| 0 | N/A | N/A | N/A | N/A | N/A | |
| NVIDIA H100 80GB PCIe | 0 | 80 GB HBM3 | 16,896 | 3.35 TB/s | 60 TFLOPS | 350 W |
| 0 | N/A | N/A | N/A | N/A | N/A | |
| NVIDIA L4 Tensor Core GPU | 0 | 24 GB GDDR6 | 7,680 | 300 GB/s | 30.3 TFLOPS | 72 W |
| NVIDIA L40 | 0 | 48 GB GDDR6 (ECC) | 18,176 | 864 GB/s | 90.5 TFLOPS | 300 W |
| NVIDIA L40S | 0 | 48 GB GDDR6 (ECC) | 18,176 | 864 GB/s | 91.6 TFLOPS | 350 W |
| Total | 779 | - | 10,892,288 | - | - | 449,950 W |
Serverless AI Compute
Node Growth Analytics
GPU node growth patterns over the last 30 days
GPU Node Counts
Below are the current counts of GPU nodes on the Chutes platform, with various statistics on the GPUs themselves, and summaries of the total compute currently available.
GPU Node Table
Below are the current counts of GPU nodes on the Chutes platform, with various statistics on the GPUs themselves, and summaries of the total compute currently available.
| GPU Name | Provisioned | Memory | CUDA Cores | Memory Bandwidth | FP32 Performance | Max Power |
|---|---|---|---|---|---|---|
| NVIDIA H200 141GB SXM | 631 | 141 GB HBM3e | 16,896 | 4.8 TB/s | 67 TFLOPS | 700 W |
| 123 | N/A | N/A | N/A | N/A | N/A | |
| NVIDIA RTX A6000 | 11 | 48 GB GDDR6 (ECC) | 10,752 | 768 GB/s | 38.7 TFLOPS | 300 W |
| NVIDIA A100 80GB SXM | 6 | 80 GB HBM2e | 6,912 | 2.039 TB/s | 19.5 TFLOPS | 400 W |
| 3 | N/A | N/A | N/A | N/A | N/A | |
| NVIDIA GeForce RTX 3090 | 2 | 24 GB GDDR6X | 10,496 | 936 GB/s | ~35.7 TFLOPS | 350 W |
| NVIDIA H100 80GB SXM | 2 | 80 GB HBM3 | 16,896 | 3.35 TB/s | 67 TFLOPS | 700 W |
| NVIDIA GeForce RTX 4090 | 1 | 24 GB GDDR6X | 16,384 | 1008 GB/s | ~83 TFLOPS | 450 W |
| NVIDIA A100 80GB PCIe | 0 | 80 GB HBM2e | 6,912 | 1.935 TB/s | 19.5 TFLOPS | 300 W |
| NVIDIA A100 40GB PCIe | 0 | 40 GB HBM2 | 6,912 | 1.6 TB/s | 19.5 TFLOPS | 250 W |
| NVIDIA A100 40GB SXM | 0 | 40 GB HBM2 | 6,912 | 1.6 TB/s | 19.5 TFLOPS | 400 W |
| NVIDIA A40 | 0 | 48 GB GDDR6 (ECC) | 10,752 | 696 GB/s | 37.4 TFLOPS | 300 W |
| NVIDIA RTX A4000 | 0 | 16 GB GDDR6 (ECC) | 6,144 | 448 GB/s | 19.2 TFLOPS | 140 W |
| NVIDIA RTX A5000 | 0 | 24 GB GDDR6 (ECC) | 8,192 | 768 GB/s | 27.8 TFLOPS | 230 W |
| NVIDIA RTX 6000 Ada Generation | 0 | 48 GB GDDR6 (ECC) | 18,176 | 960 GB/s | 91.1 TFLOPS | 300 W |
| NVIDIA B200 Blackwell | 0 | 192 GB HBM3E | 18,000 | 8 TB/s | 160 TFLOPS | 700 W |
| 0 | N/A | N/A | N/A | N/A | N/A | |
| NVIDIA H100 80GB PCIe | 0 | 80 GB HBM3 | 16,896 | 3.35 TB/s | 60 TFLOPS | 350 W |
| 0 | N/A | N/A | N/A | N/A | N/A | |
| NVIDIA L4 Tensor Core GPU | 0 | 24 GB GDDR6 | 7,680 | 300 GB/s | 30.3 TFLOPS | 72 W |
| NVIDIA L40 | 0 | 48 GB GDDR6 (ECC) | 18,176 | 864 GB/s | 90.5 TFLOPS | 300 W |
| NVIDIA L40S | 0 | 48 GB GDDR6 (ECC) | 18,176 | 864 GB/s | 91.6 TFLOPS | 350 W |
| Total | 779 | - | 10,892,288 | - | - | 449,950 W |
Serverless AI Compute