Explore Lambda's A6000 cloud instance specifications and benchmarks. Compare hardware configurations and performance metrics to optimize your AI and ML workloads.
LLM Benchmark Comparison
Hardware Specifications
| GPU Configuration | Value |
|---|---|
| GPU Type | A6000 |
| GPU Interconnect | PCIE |
| GPU Model Name | NVIDIA RTX A6000 |
| Driver Version | 535.129.03 |
| GPU VRAM | 48 |
| Power Limit (W) | 300.00 |
| GPU Temperature (°C) | 32 |
| GPU Clock Speed (MHz) | 0 |
| Memory Clock Speed (MHz) | 405 |
| Pstate | P8 |
| CPU Configuration | Value |
|---|---|
| Model Name | AMD EPYC-Rome Processor |
| Vendor ID | AuthenticAMD |
| CPUs | 14 |
| CPU Clock Speed | 4999.18 |
| Threads Per Core | 1 |
| Cores Per Socket | 1 |
| Sockets | 14 |
| Memory | Value |
|---|---|
| Total | 98Gb |
Disks Specifications
| Storage | Value |
|---|---|
| Total | 512.00GB |
Available Disks
| Property | Value |
|---|---|
| Disk 1 | |
| Model | vda |
| Size | 512Gb |
| Type | HDD |
| Mount Point | Unmounted |
Software Specifications
| Software | Value |
|---|---|
| OS | Ubuntu |
| OS Version | 22.04.3 LTS (Jammy Jellyfish) |
| Cuda Driver | 12.2 |
| Docker Version | 24.0.7 |
| Python Version | Python 3.10.12 |
Benchmarks
powered by
| Benchmark | Value |
|---|---|
| ffmpeg | 172 |
| Coremark (Itterations per sec) | 24995.834 |
| llama2Inference (Tokens per sec) | 44.36 |
| Tensorflow Mnist Training | 4.092 |
Nvidia-smi output
Nvidia-smi topo -m outpu