NVIDIA RTX PRO 6000

Consumer GPU · Blackwell · Server and Workstation editions

Summary

The RTX PRO 6000 is a versatile and powerful GPU, with applications from model training to LLM inference to graphics rendering. There are two separate editions available, built around the same chip but with different power/cooling configurations: RTX PRO 6000 Server and RTX PRO 6000 Workstation. The former is widely available among cloud providers, whereas the latter is generally only available on peer-to-peer/marketplace style providers.

Launched
Q2 2025
VRAM
96 GB
Mem. bandwidth
1,597 - 1,792 GB/s
On-demand from
Compare prices from 18 providers →

Tech specs

Spec RTX Pro 6000 SERTX Pro 6000 WS
VRAM 96 GB GDDR796 GB GDDR7
Memory bandwidth 1,597 GB/s1,792 GB/s
Interface PCIe PCIe
CUDA cores 24,064 24,064
Tensor cores 752 (Gen 5)752 (Gen 5)
TDP 600 W600 W
Supported data types
FP64FP32TF32FP16BF16FP8FP6FP4INT8

Cloud rental prices

18 providers · available in 19 countries · lowest price per GPU, per hour

Prices updated

On-demand
$1.29 – $1.34 /GPU/h
Spot
$0.53 – $1.34 /GPU/h
Provider On-demand Reserved Spot
Vast.ai $1.29 $0.53
Compare all RTX Pro 6000 WS cloud providers & configurations →

Models that fit in VRAM

Total VRAM From 16-bit inference 8-bit inference 4-bit inference
1× RTX PRO 6000 96 GB $0.72/h GLM-4.7-FlashQwen3-Coder-30B-A3B-InstructNVIDIA-Nemotron-3-Nano-30B-A3B-BF16 Qwen3-Coder-NextGLM-4.7-FlashNVIDIA-Nemotron-3-Nano-30B-A3B-BF16 DeepSeek-V4-Flashgpt-oss-120bNVIDIA-Nemotron-3-Super-120B-A12B-BF16
2× RTX PRO 6000 192 GB $1.44/h Qwen3-Coder-NextGLM-4.7-FlashNVIDIA-Nemotron-3-Nano-30B-A3B-BF16 DeepSeek-V4-Flashgpt-oss-120bNVIDIA-Nemotron-3-Super-120B-A12B-BF16 MiniMax-M2.7DeepSeek-V4-Flashgpt-oss-120b
3× RTX PRO 6000 288 GB $5.97/h gpt-oss-120bNVIDIA-Nemotron-3-Super-120B-A12B-BF16GLM-4.5-Air MiniMax-M2.7DeepSeek-V4-Flashgpt-oss-120b MiniMax-M2.7DeepSeek-V4-Flashgpt-oss-120b
4× RTX PRO 6000 384 GB $4.83/h DeepSeek-V4-Flashgpt-oss-120bNVIDIA-Nemotron-3-Super-120B-A12B-BF16 MiniMax-M2.7DeepSeek-V4-Flashgpt-oss-120b MiniMax-M2.7DeepSeek-V4-Flashgpt-oss-120b
5× RTX PRO 6000 480 GB $9.95/h DeepSeek-V4-Flashgpt-oss-120bNVIDIA-Nemotron-3-Super-120B-A12B-BF16 MiniMax-M2.7DeepSeek-V4-Flashgpt-oss-120b DeepSeek-V4-ProMiniMax-M2.7gpt-oss-120b
6× RTX PRO 6000 576 GB $11.94/h MiniMax-M2.7DeepSeek-V4-Flashgpt-oss-120b MiniMax-M2.7DeepSeek-V4-Flashgpt-oss-120b DeepSeek-V4-ProMiniMax-M2.7gpt-oss-120b
7× RTX PRO 6000 672 GB $13.93/h MiniMax-M2.7DeepSeek-V4-Flashgpt-oss-120b MiniMax-M2.7DeepSeek-V4-Flashgpt-oss-120b Kimi-K2-Instruct-0905DeepSeek-V4-ProMiniMax-M2.7
8× RTX PRO 6000 768 GB $9.66/h MiniMax-M2.7DeepSeek-V4-Flashgpt-oss-120b MiniMax-M2.7DeepSeek-V4-Flashgpt-oss-120b Kimi-K2-Instruct-0905DeepSeek-V4-ProMiniMax-M2.7

Open-weights models that fit in VRAM. Estimated using 🤗 accelerate, plus approximation for up to 8K context.

Media

Peak theoretical performance

Spec RTX Pro 6000 SERTX Pro 6000 WS
FP4 Tensor Core 2,000 TFLOPS2,000 TFLOPS
FP32 120 TFLOPS125 TFLOPS
RT Core 355 TFLOPS380 TFLOPS

Performance figures assume no sparsity; in cases where only sparse performance figures are published by the manufacturer, these are halved to give approximate dense performance.

Resources

Detailed documentation from the manufacturer.

Similar GPUs

Other accelerators you might compare.