Skip to content
Updated minutes ago
nvidia

RTX 6000 Ada

nvidia · ada · 48 GB GDDR6 · 300W TDP

VRAM

48 GB

BF16 TFLOPS

91.1

Bandwidth

960 GB/s

From

$0.59/hr

Calculate ROI with this GPU →

Spec Sheet

VRAM48 GB GDDR6
Memory Bandwidth960 GB/s
BF16 TFLOPS91.1
FP16 TFLOPS91.1
FP8 TFLOPS182.2
INT8 TOPS182.2
TDP300W
InterconnectPCIE
Max per Node8
PCIe Gen4
CUDA Compute Capability8.9
Tensor CoresYes

Pricing by Provider

ProviderOn-DemandReservedSpotBadge
tensordock$0.79/hr-$0.59/hrCheapest
vast_ai$0.89/hr-$0.65/hr
runpod$1.29/hr-$0.99/hr
lambda$1.09/hr--

Compatible Models (267)

Training Capabilities

Estimated GPU count for full fine-tuning (AdamW, BF16) and QLoRA

Model SizeFull Fine-TuneQLoRA
7B model3 GPUs1 GPU
13B model6 GPUs1 GPU
70B model28 GPUs1 GPU

Energy Efficiency

Estimated tokens/second per Watt for popular models

Mistral 7B
0.44 t/s/WFP8
Qwen 2.5 7B
0.42 t/s/WFP8
Llama 3.1 8B
0.40 t/s/WFP8
Llama 3.1 70B
0.05 t/s/WFP8
Qwen 2.5 72B
0.04 t/s/WFP8

Similar GPUs

GPUVRAMBF16 TFLOPSBW (GB/s)From
L40S48 GB362864$0.85/hr
L4048 GB362864$0.75/hr
L2048 GB239864$0.80/hr
L424 GB121300$0.29/hr
RTX 409024 GB1651008$0.39/hr

Methodology Note

Performance estimates for the RTX 6000 Adaare based on InferenceBench's roofline performance model with CUDA kernel-level optimization including FlashAttention v2 and PagedAttention. Memory calculations account for model weights (48 GB GDDR6 available), KV-cache allocation, and activation memory. Throughput predictions use the RTX 6000 Ada's rated 960 GB/s memory bandwidth and 91.1 BF16 TFLOPS compute capacity as roofline ceilings, with empirical correction factors per GPU architecture (ada). See our full methodology.

Frequently Asked Questions

How many AI models can run on RTX 6000 Ada?

The RTX 6000 Ada can run 267 AI models from our database within a single node. Compatible models range across various parameter sizes depending on the quantization precision (BF16, FP8, INT4). Smaller models fit on a single GPU while larger models may require multi-GPU setups up to 8x RTX 6000 Ada.

What is the RTX 6000 Ada inference throughput?

The RTX 6000 Ada delivers 91.1 BF16 TFLOPS and 182.2 FP8 TFLOPS with 960 GB/s memory bandwidth. Actual inference throughput (tokens/sec) depends on the model size, precision, and batch size. Use our calculator for model-specific throughput estimates.

How much does RTX 6000 Ada cost per hour?

The RTX 6000 Ada is available starting from $0.59/hour via tensordock. Prices vary by provider and pricing tier (on-demand, reserved, spot). Compare pricing across all providers in the table above.