NVIDIA RTX PRO 6000 SE GPU: Specs, VRAM, Price & Benchmarks (2026)
The NVIDIA RTX PRO 6000 SE (96GB GDDR7) 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 SE rents from $2.22 per GPU per hour on Aquanode.
How much VRAM does the RTX PRO 6000 SE have?
The RTX PRO 6000 SE has 96GB GDDR7, with 1,597 GB/s of peak memory bandwidth.
What fits in 96GB GDDR7 of VRAM
| Model | Precision | Fits? |
|---|---|---|
| Llama 3.1 70B | FP8 | roughly 70GB. Fits on one card with context headroom. |
| Llama 3.1 70B | FP16 | ~140GB. Does not fit on one 96GB card; needs 2. |
| Mixtral 8x22B | INT4 | ~70GB. Fits on a single card. |
| Llama 3.1 405B | INT4 | ~200-230GB. Needs 3 cards. |
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 SE run?
Popular open models from small to frontier scale, with the memory each needs and how many RTX PRO 6000 SE cards (96GB GDDR7 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 SE VRAM calculator.
RTX PRO 6000 SE 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 SE specs
| Architecture | NVIDIA, launched 2025 |
| VRAM | 96GB GDDR7 |
| Memory bandwidth | 1,597 GB/s |
| TDP | Up to 600W (configurable) |
| Form factor | PCIe, dual-slot (air), PCIe, single-slot (liquid) |
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 SE AI performance
The rack version of the 96GB Blackwell workstation card. Same capacity, passively cooled for a server chassis, and available in a single-slot liquid-cooled form that racks denser than any other 96GB part here. Enough VRAM to serve a 70B model in FP8 on one GPU with real context headroom.
- Memory bandwidth: 1,597 GB/s
1,597 GB/s is below the Workstation Edition's 1,792 GB/s despite the identical 96GB, so it is the slower of the two on memory-bound serving. No NVLink either, so multi-GPU work goes over PCIe.
RTX PRO 6000 SE price: what does it cost?
Renting. The cheapest current on-demand rate for the RTX PRO 6000 SE on Aquanode is $2.22/GPU/hr (no on-demand supply right now; this is the cheapest offer overall). Live rates range from $2.22 to $2.22 per GPU per hour, with a median of $2.22/GPU/hr. Billed by the offer's own terms; the table below shows every live rate.
| Region | $/GPU/hr | Available | VRAM | vCPU | RAM |
|---|---|---|---|---|---|
| Rdu, Us | $2.22 | 20 | 96 GB | 28.3 | 497.4 GB |
RTX PRO 6000 SE price history
Aquanode stores one snapshot of its GPU price index per UTC day. For the RTX PRO 6000 SE 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 $2.15 on 2026-10-06 to $2.22 on 2026-10-30.
| Day (UTC) | Lowest per GPU hour | Median per GPU hour | Data-center lowest per GPU hour | Offers |
|---|---|---|---|---|
| 2026-10-30 | $2.22 | $2.22 | – | 1 |
| 2026-10-29 | $2.22 | $2.22 | – | 2 |
| 2026-10-28 | $2.15 | $2.15 | – | 1 |
| 2026-10-27 | $2.15 | $2.15 | – | 1 |
| 2026-10-26 | $2.15 | $2.15 | – | 1 |
| 2026-10-25 | $2.15 | $2.15 | – | 2 |
| 2026-10-24 | $2.15 | $2.15 | – | 1 |
| 2026-10-23 | $2.15 | $2.15 | – | 2 |
| 2026-10-22 | $2.04 | $2.04 | – | 1 |
| 2026-10-21 | $2.15 | $2.15 | – | 1 |
| 2026-10-20 | $2.15 | $2.15 | – | 1 |
| 2026-10-19 | $2.15 | $2.15 | – | 1 |
| 2026-10-18 | $2.15 | $2.15 | – | 1 |
| 2026-10-17 | $2.15 | $2.15 | – | 1 |
| 2026-10-16 | $2.15 | $2.15 | – | 1 |
| 2026-10-15 | $2.15 | $2.15 | – | 1 |
| 2026-10-14 | $2.15 | $2.15 | – | 1 |
| 2026-10-13 | $2.15 | $2.15 | – | 1 |
| 2026-10-12 | $2.15 | $2.15 | – | 1 |
| 2026-10-11 | $2.15 | $2.15 | – | 1 |
| 2026-10-10 | $2.15 | $2.15 | – | 2 |
| 2026-10-09 | $2.15 | $2.15 | – | 2 |
| 2026-10-08 | $2.15 | $2.15 | – | 1 |
| 2026-10-07 | $2.15 | $2.15 | – | 1 |
| 2026-10-06 | $2.15 | $2.15 | – | 1 |
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 SE with other GPUs
Compare RTX PRO 6000 SE with
- B200 vs RTX PRO 6000 SE
- H200 vs RTX PRO 6000 SE
- H100 vs RTX PRO 6000 SE
- A100 vs RTX PRO 6000 SE
- DGX A100 vs RTX PRO 6000 SE
- RTX PRO 6000 SE vs V100
- AMD MI300X vs RTX PRO 6000 SE
- L40S vs RTX PRO 6000 SE
- L40 vs RTX PRO 6000 SE
- A40 vs RTX PRO 6000 SE
- RTX A6000 vs RTX PRO 6000 SE
- RTX A5000 vs RTX PRO 6000 SE
- RTX A4000 vs RTX PRO 6000 SE
- L4 vs RTX PRO 6000 SE
- RTX PRO 6000 SE vs T4
- RTX 6000 Ada vs RTX PRO 6000 SE
- RTX PRO 6000 vs RTX PRO 6000 SE
- RTX PRO 6000 SE vs RTX PRO 6000 WS
- RTX PRO 5000 vs RTX PRO 6000 SE
- RTX 5090 vs RTX PRO 6000 SE
- RTX 5080 vs RTX PRO 6000 SE
- RTX 5070 Ti vs RTX PRO 6000 SE
- RTX 5070 vs RTX PRO 6000 SE
- RTX 5060 Ti vs RTX PRO 6000 SE
- RTX 4090 vs RTX PRO 6000 SE
- RTX 4080 Super vs RTX PRO 6000 SE
- RTX 4080 vs RTX PRO 6000 SE
- RTX 4070 Ti vs RTX PRO 6000 SE
- RTX 4070 Super vs RTX PRO 6000 SE
- RTX 4070 vs RTX PRO 6000 SE
- RTX 4060 Ti vs RTX PRO 6000 SE
- RTX 3090 vs RTX PRO 6000 SE
- RTX 3080 vs RTX PRO 6000 SE
- RTX 3070 vs RTX PRO 6000 SE
- RTX 3060 vs RTX PRO 6000 SE
- B300 vs RTX PRO 6000 SE
- AMD MI355X vs RTX PRO 6000 SE
- AMD MI325X vs RTX PRO 6000 SE
- H100 NVL vs RTX PRO 6000 SE
- RTX PRO 4500 vs RTX PRO 6000 SE
- RTX PRO 4500 SE vs RTX PRO 6000 SE
- RTX PRO 4000 vs RTX PRO 6000 SE
- RTX 5880 Ada vs RTX PRO 6000 SE
- RTX 5000 Ada vs RTX PRO 6000 SE
- RTX 4000 Ada vs RTX PRO 6000 SE
- RTX 4000 SFF Ada vs RTX PRO 6000 SE
- RTX 2000 Ada vs RTX PRO 6000 SE
- RTX 4070 Ti Super vs RTX PRO 6000 SE
- RTX A4500 vs RTX PRO 6000 SE
- RTX 2080 Ti vs RTX PRO 6000 SE
- RTX 3080 Ti vs RTX PRO 6000 SE
- RTX 3070 Ti vs RTX PRO 6000 SE
- RTX 3060 Ti vs RTX PRO 6000 SE
- GTX 1080 Ti vs RTX PRO 6000 SE
- RTX 4060 vs RTX PRO 6000 SE
- RTX 5060 vs RTX PRO 6000 SE
- GTX 1660 Super vs RTX PRO 6000 SE
- RTX 2060 vs RTX PRO 6000 SE
- Radeon RX 9070 XT vs RTX PRO 6000 SE
- Radeon RX 6700 XT vs RTX PRO 6000 SE
- RTX 6000 vs RTX PRO 6000 SE
- A16 vs RTX PRO 6000 SE
- P40 vs RTX PRO 6000 SE
- P4 vs RTX PRO 6000 SE
- Quadro P2000 vs RTX PRO 6000 SE
- Quadro M4000 vs RTX PRO 6000 SE
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 SE on Aquanode
- On-demand instances from $2.22/GPU/hr, billed by the provider's own terms, with no hardware procurement or long-term commitment.
- 1 live offer across 1 region today.
- Set a price/availability alert above to hear the moment a cheaper or newly-available RTX PRO 6000 SE offer appears.
- Compare every RTX PRO 6000 SE offer side by side, or browse the full multi-provider GPU marketplace.
Good for
The rack version of the 96GB Blackwell workstation card. Same capacity, passively cooled for a server chassis, and available in a single-slot liquid-cooled form that racks denser than any other 96GB part here. Enough VRAM to serve a 70B model in FP8 on one GPU with real context headroom.
Not good for
1,597 GB/s is below the Workstation Edition's 1,792 GB/s despite the identical 96GB, so it is the slower of the two on memory-bound serving. No NVLink either, so multi-GPU work goes over PCIe.
RTX PRO 6000 SE FAQs
How much VRAM does the RTX PRO 6000 SE have?
The RTX PRO 6000 SE has 96GB GDDR7, with 1,597 GB/s of peak memory bandwidth.
What is the NVIDIA RTX PRO 6000 SE?
The NVIDIA RTX PRO 6000 SE is a GPU released in 2025, with 96GB GDDR7 of memory and a Up to 600W (configurable) 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 SE?
Live RTX PRO 6000 SE rental prices currently range from $2.22 to $2.22 per GPU per hour, with a median of $2.22 per GPU per hour.
What's the cheapest RTX PRO 6000 SE rate?
The lowest current RTX PRO 6000 SE rate on Aquanode is $2.22 per GPU per hour in Rdu, Us.
What is the RTX PRO 6000 SE good for?
The rack version of the 96GB Blackwell workstation card. Same capacity, passively cooled for a server chassis, and available in a single-slot liquid-cooled form that racks denser than any other 96GB part here. Enough VRAM to serve a 70B model in FP8 on one GPU with real context headroom.
What are the RTX PRO 6000 SE's limitations?
1,597 GB/s is below the Workstation Edition's 1,792 GB/s despite the identical 96GB, so it is the slower of the two on memory-bound serving. No NVLink either, so multi-GPU work goes over PCIe.
Is renting cheaper than buying?
Renting avoids the upfront hardware cost and lets you match spend to actual usage. A rented RTX PRO 6000 SE at $2.22/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 SE 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 SE price by region
Related guides
Other models in the same generation, then the rest of the GPU index.
