Skip to content
Updated minutes ago
nvidia

RTX A6000

nvidia · ampere · 48 GB GDDR6 · 300W TDP

VRAM

48 GB

BF16 TFLOPS

38.7

Bandwidth

768 GB/s

From

$0.49/hr

Calculate ROI with this GPU →

Spec Sheet

VRAM48 GB GDDR6
Memory Bandwidth768 GB/s
BF16 TFLOPS38.7
FP16 TFLOPS38.7
FP8 TFLOPS38.7
INT8 TOPS77.4
TDP300W
InterconnectPCIE
Max per Node8
PCIe Gen4
CUDA Compute Capability8.6
Tensor CoresYes

Pricing by Provider

ProviderOn-DemandReservedSpotBadge
tensordock$0.69/hr-$0.49/hrCheapest
vast_ai$0.79/hr-$0.55/hr
runpod$1.09/hr-$0.79/hr
lambda$0.99/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
0.35 t/s/WFP8
Qwen 2.5 7B
0.34 t/s/WFP8
Llama 3.1 8B
0.32 t/s/WFP8
Llama 3.1 70B
0.04 t/s/WFP8
Qwen 2.5 72B
0.04 t/s/WFP8

Similar GPUs

GPUVRAMBF16 TFLOPSBW (GB/s)From
A4048 GB37.4696$0.42/hr
A100 40GB SXM40 GB3121555$0.85/hr
A100 40GB PCIe40 GB3121555$0.69/hr
A1664 GB16.8232$0.72/hr
A10G24 GB35600$0.30/hr

Methodology Note

Performance estimates for the RTX A6000are 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 A6000's rated 768 GB/s memory bandwidth and 38.7 BF16 TFLOPS compute capacity as roofline ceilings, with empirical correction factors per GPU architecture (ampere). See our full methodology.

Frequently Asked Questions

How many AI models can run on RTX A6000?

The RTX A6000 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 A6000.

What is the RTX A6000 inference throughput?

The RTX A6000 delivers 38.7 BF16 TFLOPS and 38.7 FP8 TFLOPS with 768 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 A6000 cost per hour?

The RTX A6000 is available starting from $0.49/hour via tensordock. Prices vary by provider and pricing tier (on-demand, reserved, spot). Compare pricing across all providers in the table above.