NVIDIA RTX PRO 6000 WS GPU: Specs, VRAM, Price & Benchmarks (2026)
The NVIDIA RTX PRO 6000 WS (96GB GDDR7 with ECC) launched in 2025. This guide covers its full specs, VRAM, SXM/PCIe differences where they apply, AI performance, and live per-GPU rental pricing on Aquanode.
Short answer on cost: the RTX PRO 6000 WS rents from $1.98 per GPU per hour on Aquanode.
How much VRAM does the RTX PRO 6000 WS have?
The RTX PRO 6000 WS has 96GB GDDR7 with ECC, with 1,792 GB/s of peak memory bandwidth.
What fits in 96GB GDDR7 with ECC of VRAM
| Model | Precision | Fits? |
|---|---|---|
| Llama 3.1 70B | FP16 | roughly 140GB. Does not fit on one 96GB card; needs 2. |
| Llama 3.1 70B | INT4 | ~35-40GB. Fits with plenty of headroom. |
| Mixtral 8x22B | INT4 | ~70GB. Fits on a single card. |
| Llama 3 8B | FP16 | ~16GB. Fits easily. |
Approximate, based on published parameter counts and standard bytes-per-parameter rules of thumb (FP16 ≈ 2 bytes/param, INT4 ≈ 0.5-0.6 bytes/param). Real footprint also depends on KV-cache size and framework overhead.
What can the RTX PRO 6000 WS run?
Popular open models from small to frontier scale, with the memory each needs and how many RTX PRO 6000 WS cards (96GB GDDR7 with ECC each) that takes.
| Model | As published | FP8 | INT4 |
|---|---|---|---|
| Qwen/Qwen3-8B 8.2B | BF16: ~18.3 GB, 1 GPU | FP8: ~9.2 GB, 1 GPU | INT4: ~4.6 GB, 1 GPU |
| Qwen/Qwen2.5-14B-Instruct 14.8B | BF16: ~33 GB, 1 GPU | FP8: ~16.5 GB, 1 GPU | INT4: ~8.3 GB, 1 GPU |
| Qwen/Qwen3-32B 32.8B | BF16: ~73.2 GB, 1 GPU | FP8: ~36.6 GB, 1 GPU | INT4: ~18.3 GB, 1 GPU |
| Qwen/Qwen-72B 72.3B | BF16: ~162 GB, 2 GPUs | FP8: ~80.8 GB, 1 GPU | INT4: ~40.4 GB, 1 GPU |
| MiniMaxAI/MiniMax-M2.7 228.7B | FP8: ~256 GB, 3 GPUs | – | INT4: ~128 GB, 2 GPUs |
| deepseek-ai/DeepSeek-R1 684.5B | FP8: ~765 GB, 8 GPUs | – | INT4: ~383 GB, 4 GPUs |
Estimates: weights at the stated precision plus a flat 20% for KV cache and overhead, at a moderate context length. A dash means the precision is not offered for that model (it is already published at that size). INT4 needs a published quantized checkpoint. Open any model for a per-GPU breakdown, or use the RTX PRO 6000 WS VRAM calculator.
RTX PRO 6000 WS VRAM calculator: check which models fit in its memory at each precision.
All models that fit in 96 GB: the open models whose weights and overhead fit, at native, FP8 and INT4 precision.
RTX PRO 6000 WS specs
| Architecture | NVIDIA, launched 2025 |
| VRAM | 96GB GDDR7 with ECC |
| Memory bandwidth | 1,792 GB/s |
| TDP | 600W |
| Form factor | PCIe, dual-slot |
Specs sourced from the vendor's public datasheet/product page. See the source.
Related reading: The NVIDIA Inception program, explained, Google Colab alternatives for dedicated GPU access, Free GPU credits for students and researchers, and RunPod volume disk vs. network volume, compared.
GPU Glossary: What is VRAM?, Tensor Cores, CUDA Cores, TFLOPS
RTX PRO 6000 WS AI performance
The workstation-desktop build of the RTX PRO 6000: 96GB of ECC GDDR7 at 1,792 GB/s, actively cooled, in a machine under a desk. It holds a 70B model at FP8 (about 70GB of weights) on one card, which no other workstation part listed here does.
- Memory bandwidth: 1,792 GB/s
600W and no NVLink. Scaling past one card means PCIe, and two of these need a power budget most workstations don't have. If the job fits in 48GB, an RTX 6000 Ada does it at half the power.
The cheapest RTX PRO 6000 WS offer right now ($1.98/GPU/hr) is about 4% below the market median of $2.06/GPU/hr.
RTX PRO 6000 WS price: what does it cost?
Renting. The cheapest current on-demand rate for the RTX PRO 6000 WS on Aquanode is $1.98/GPU/hr (no on-demand supply right now; this is the cheapest offer overall). Live rates range from $1.98 to $2.34 per GPU per hour, with a median of $2.06/GPU/hr. Billed by the offer's own terms; the table below shows every live rate.
| Region | $/GPU/hr | Available | VRAM | vCPU | RAM |
|---|---|---|---|---|---|
| Washington, Us | $1.98 | 2 | 96 GB | 32 | 125.5 GB |
RTX PRO 6000 WS price history
Aquanode stores one snapshot of its GPU price index per UTC day. For the RTX PRO 6000 WS that is 25 days so far, 2026-10-06 to 2026-10-30, so this is a short history, not a long-run trend. The lowest per-GPU rate went from $1.66 on 2026-10-06 to $1.72 on 2026-10-30.
| Day (UTC) | Lowest per GPU hour | Median per GPU hour | Data-center lowest per GPU hour | Offers |
|---|---|---|---|---|
| 2026-10-30 | $1.72 | $1.88 | – | 13 |
| 2026-10-29 | $1.67 | $1.75 | – | 9 |
| 2026-10-28 | $1.54 | $1.82 | – | 5 |
| 2026-10-27 | $1.79 | $1.87 | – | 4 |
| 2026-10-26 | $1.76 | $2.22 | – | 6 |
| 2026-10-25 | $1.90 | $2.21 | – | 7 |
| 2026-10-24 | $1.76 | $1.93 | – | 6 |
| 2026-10-23 | $1.76 | $2.14 | – | 4 |
| 2026-10-22 | $1.76 | $2.38 | – | 3 |
| 2026-10-21 | $1.64 | $1.95 | – | 6 |
| 2026-10-20 | $1.50 | $1.76 | – | 6 |
| 2026-10-19 | $1.66 | $2.06 | – | 13 |
| 2026-10-18 | $1.50 | $1.92 | – | 12 |
| 2026-10-17 | $1.54 | $1.91 | – | 8 |
| 2026-10-16 | $1.73 | $1.95 | – | 4 |
| 2026-10-15 | $1.60 | $1.76 | – | 8 |
| 2026-10-14 | $1.60 | $1.80 | – | 13 |
| 2026-10-13 | $1.62 | $1.80 | – | 11 |
| 2026-10-12 | $1.55 | $1.79 | – | 6 |
| 2026-10-11 | $1.60 | $1.74 | – | 12 |
| 2026-10-10 | $1.45 | $1.76 | – | 11 |
| 2026-10-09 | $1.65 | $1.87 | – | 10 |
| 2026-10-08 | $1.58 | $1.76 | – | 16 |
| 2026-10-07 | $1.54 | $2.03 | – | 8 |
| 2026-10-06 | $1.66 | $2.03 | – | 13 |
Each row is the stored daily snapshot of the live index, copied as recorded. A dash means that day stored no figure. The same series is available as JSON and summarised in the monthly GPU price report.
How this price is calculated
All prices on this page are normalized to a per-GPU hourly rate using each offer's authoritative GPU count, so that raw price is divided by the number of GPUs it actually covers; some offers report price as already per-GPU, so those are used as-listed. An offer with a missing, zero, or invalid GPU count is excluded entirely rather than published at a guessed rate.
No offers were excluded from this snapshot for a missing or invalid price. No offers were dropped as price outliers in this snapshot.
Only the cheapest qualifying offer per provider is shown in the table above. This page regenerates at most once per hour.
Compare the RTX PRO 6000 WS with other GPUs
Compare RTX PRO 6000 WS with
- B200 vs RTX PRO 6000 WS
- H200 vs RTX PRO 6000 WS
- H100 vs RTX PRO 6000 WS
- A100 vs RTX PRO 6000 WS
- DGX A100 vs RTX PRO 6000 WS
- RTX PRO 6000 WS vs V100
- AMD MI300X vs RTX PRO 6000 WS
- L40S vs RTX PRO 6000 WS
- L40 vs RTX PRO 6000 WS
- A40 vs RTX PRO 6000 WS
- RTX A6000 vs RTX PRO 6000 WS
- RTX A5000 vs RTX PRO 6000 WS
- RTX A4000 vs RTX PRO 6000 WS
- L4 vs RTX PRO 6000 WS
- RTX PRO 6000 WS vs T4
- RTX 6000 Ada vs RTX PRO 6000 WS
- RTX PRO 6000 vs RTX PRO 6000 WS
- RTX PRO 6000 SE vs RTX PRO 6000 WS
- RTX PRO 5000 vs RTX PRO 6000 WS
- RTX 5090 vs RTX PRO 6000 WS
- RTX 5080 vs RTX PRO 6000 WS
- RTX 5070 Ti vs RTX PRO 6000 WS
- RTX 5070 vs RTX PRO 6000 WS
- RTX 5060 Ti vs RTX PRO 6000 WS
- RTX 4090 vs RTX PRO 6000 WS
- RTX 4080 Super vs RTX PRO 6000 WS
- RTX 4080 vs RTX PRO 6000 WS
- RTX 4070 Ti vs RTX PRO 6000 WS
- RTX 4070 Super vs RTX PRO 6000 WS
- RTX 4070 vs RTX PRO 6000 WS
- RTX 4060 Ti vs RTX PRO 6000 WS
- RTX 3090 vs RTX PRO 6000 WS
- RTX 3080 vs RTX PRO 6000 WS
- RTX 3070 vs RTX PRO 6000 WS
- RTX 3060 vs RTX PRO 6000 WS
- B300 vs RTX PRO 6000 WS
- AMD MI355X vs RTX PRO 6000 WS
- AMD MI325X vs RTX PRO 6000 WS
- H100 NVL vs RTX PRO 6000 WS
- RTX PRO 4500 vs RTX PRO 6000 WS
- RTX PRO 4500 SE vs RTX PRO 6000 WS
- RTX PRO 4000 vs RTX PRO 6000 WS
- RTX 5880 Ada vs RTX PRO 6000 WS
- RTX 5000 Ada vs RTX PRO 6000 WS
- RTX 4000 Ada vs RTX PRO 6000 WS
- RTX 4000 SFF Ada vs RTX PRO 6000 WS
- RTX 2000 Ada vs RTX PRO 6000 WS
- RTX 4070 Ti Super vs RTX PRO 6000 WS
- RTX A4500 vs RTX PRO 6000 WS
- RTX 2080 Ti vs RTX PRO 6000 WS
- RTX 3080 Ti vs RTX PRO 6000 WS
- RTX 3070 Ti vs RTX PRO 6000 WS
- RTX 3060 Ti vs RTX PRO 6000 WS
- GTX 1080 Ti vs RTX PRO 6000 WS
- RTX 4060 vs RTX PRO 6000 WS
- RTX 5060 vs RTX PRO 6000 WS
- GTX 1660 Super vs RTX PRO 6000 WS
- RTX 2060 vs RTX PRO 6000 WS
- Radeon RX 9070 XT vs RTX PRO 6000 WS
- Radeon RX 6700 XT vs RTX PRO 6000 WS
- RTX 6000 vs RTX PRO 6000 WS
- A16 vs RTX PRO 6000 WS
- P40 vs RTX PRO 6000 WS
- P4 vs RTX PRO 6000 WS
- Quadro P2000 vs RTX PRO 6000 WS
- Quadro M4000 vs RTX PRO 6000 WS
Get notified when the price drops
GPU supply moves hourly. Tell us what you're waiting for and we'll email you when a matching offer appears across any provider we track.
Rent a RTX PRO 6000 WS on Aquanode
- On-demand instances from $1.98/GPU/hr, billed by the provider's own terms, with no hardware procurement or long-term commitment.
- 5 live offers across 1 region today.
- Set a price/availability alert above to hear the moment a cheaper or newly-available RTX PRO 6000 WS offer appears.
- Compare every RTX PRO 6000 WS offer side by side, or browse the full multi-provider GPU marketplace.
Good for
The workstation-desktop build of the RTX PRO 6000: 96GB of ECC GDDR7 at 1,792 GB/s, actively cooled, in a machine under a desk. It holds a 70B model at FP8 (about 70GB of weights) on one card, which no other workstation part listed here does.
Not good for
600W and no NVLink. Scaling past one card means PCIe, and two of these need a power budget most workstations don't have. If the job fits in 48GB, an RTX 6000 Ada does it at half the power.
RTX PRO 6000 WS FAQs
How much VRAM does the RTX PRO 6000 WS have?
The RTX PRO 6000 WS has 96GB GDDR7 with ECC, with 1,792 GB/s of peak memory bandwidth.
What is the NVIDIA RTX PRO 6000 WS?
The NVIDIA RTX PRO 6000 WS is a GPU released in 2025, with 96GB GDDR7 with ECC of memory and a 600W power envelope. See the full spec table above for interconnect, form factor and tensor-throughput details.
How much does it cost to rent a RTX PRO 6000 WS?
Live RTX PRO 6000 WS rental prices currently range from $1.98 to $2.34 per GPU per hour, with a median of $2.06 per GPU per hour.
What's the cheapest RTX PRO 6000 WS rate?
The lowest current RTX PRO 6000 WS rate on Aquanode is $1.98 per GPU per hour in Washington, Us.
What is the RTX PRO 6000 WS good for?
The workstation-desktop build of the RTX PRO 6000: 96GB of ECC GDDR7 at 1,792 GB/s, actively cooled, in a machine under a desk. It holds a 70B model at FP8 (about 70GB of weights) on one card, which no other workstation part listed here does.
What are the RTX PRO 6000 WS's limitations?
600W and no NVLink. Scaling past one card means PCIe, and two of these need a power budget most workstations don't have. If the job fits in 48GB, an RTX 6000 Ada does it at half the power.
Is renting cheaper than buying?
Renting avoids the upfront hardware cost and lets you match spend to actual usage. A rented RTX PRO 6000 WS at $1.98/hr only costs money while it's running, whereas buying ties up capital in hardware that keeps depreciating whether it's in use or not. Which is cheaper depends on how continuously you'd run it; short or bursty workloads usually favor renting.
How is the RTX PRO 6000 WS price calculated?
All prices are normalized to a per-GPU hourly rate using each offer's authoritative GPU count, which the raw price is divided by; some offers report price as already per-GPU. Offers whose price can't be safely normalized, or whose rate is an extreme outlier against the rest of the market, are excluded.
RTX PRO 6000 WS price by region
Related guides
Other models in the same generation, then the rest of the GPU index.
