Skip to content

Commit bfa7975

Browse files
v-shilsv-shils
authored
Merge pull request #2462 from magatala-MSFT/RTXPRO
Rtxpro6000BSE
2 parents 7ec79f6 + 6930ca9 commit bfa7975

File tree

2 files changed

+90
-0
lines changed

2 files changed

+90
-0
lines changed

‎articles/virtual-machines/TOC.yml‎

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -538,6 +538,8 @@
538538
href: ./sizes/gpu-accelerated/ncast4v3-series.md
539539
- name: NC_A100_v4 series
540540
href: ./sizes/gpu-accelerated/nca100v4-series.md
541+
- name: NC_RTXPRO6000BSE_v6 series
542+
href: ./sizes/gpu-accelerated/nc-rtxpro6000-bse-v6-series.md
541543
- name: ND family
542544
items:
543545
- name: Overview

‎articles/virtual-machines/sizes/gpu-accelerated/nc-rtxpro6000-bse-v6-series.md‎

Lines changed: 88 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,88 @@
1+
---
2+
title: NC_RTXPRO6000BSE_v6 series
3+
description: Information on and specifications of the NC_RTXPRO6000BSE_v6-series sizes
4+
author: magatala-MSFT
5+
ms.service: azure-virtual-machines
6+
ms.subservice: sizes
7+
ms.topic: concept-article
8+
ms.date: 11/20/2025
9+
ms.author: v-nmagatala
10+
ms.reviewer: iamwilliew
11+
# Customer intent: As a cloud architect, I want to understand the specifications and feature support of the NC_RTXPRO6000BSE_v6 size series, so that I can select the appropriate virtual machine size for my high-performance computing workloads.
12+
---
13+
14+
# NC RTXPRO6000BSE v6 series
15+
16+
These NC RTX PRO 6000 BSE v6 VMs are powered by NVIDIA RTX PRO 6000 Blackwell Server Edition GPUs, each featuring 96 GB of ultra-fast GDDR7 memory and the latest Blackwell architecture to enable breakthrough performance in multimodal AI, physical AI, and high-fidelity graphics. The VM host is equipped with Intel Granite Rapids CPUs, providing all-core turbo frequency of up to 4.2 GHz to handle demanding pre- and post-processing steps efficiently. These VMs are ideal for converged AI and visual computing workloads, such as:
17+
- Real-time digital twin and NVIDIA Omniverse simulation.
18+
- LLM Inference and RAG (Retrieval-Augmented Generation) for models under 70B parameters.
19+
- High-fidelity 3D rendering, product design, and video streaming.
20+
- GPU-accelerated desktop virtualization (VDI) with NVIDIA RTX Virtual Workstation.
21+
- Scientific visualization and High-Performance Computing (HPC) using FP32.
22+
- Agentic AI application development and deployment.
23+
24+
Sign up to Participate in [NCv6 Public Preview](https://forms.office.com/Pages/ResponsePage.aspx?id=v4j5cvGGr0GRqy180BHbR9s7orOb3OJJnwABCNj_8JdUMzlLSzJFTTdRRE8yU0UxWFFYQlpYV1hDVy4u) !
25+
26+
## Host specifications
27+
| Part | Quantity <br><sup>(Count Units) | Specs <br><sup>(SKU ID, Performance Units, etc.) |
28+
|---|---|---|
29+
|Processor|upto 320 vCPUs|Intel GNR AP (Granite Rapids-AP) [x86-64], up to 4.2 GHz|
30+
|Memory| 768 – 1536 GiB |High-speed DDR5|
31+
|Disk|8 - 16 Disks|250,000 – 500,000 IOPS (Target) / 8,000 – 15,000 MBps (Target)|
32+
|Network|2 - 4 NICs|200,000 Mbps|
33+
|Accelerators|1 - 2 GPUs|NVIDIA RTX PRO 6000 BSE (96 GB GDDR7 vRAM per GPU)|
34+
35+
36+
## Feature support
37+
[Premium Storage](../../premium-storage-performance.md): Supported <br>[Premium Storage caching](../../premium-storage-performance.md): Supported <br>[Live Migration](../../maintenance-and-updates.md): Not Supported <br>[Memory Preserving Updates](../../maintenance-and-updates.md): Not Supported <br>[Generation 2 VMs](../../generation-2.md): Supported <br>[Generation 1 VMs](../../generation-2.md): Not Supported <br>[Accelerated Networking](/azure/virtual-network/create-vm-accelerated-networking-cli): Supported <br>[Ephemeral OS Disk](../../ephemeral-os-disks.md): Supported <br>[Nested Virtualization](/virtualization/hyper-v-on-windows/user-guide/nested-virtualization): Not Supported <br>
38+
39+
## Available sizes
40+
41+
### [General Purpose](#tab/sizegeneralpurpose)
42+
43+
| Size Name | vCPUs (Qty.) | Memory (GB) | Max NICs (Qty.)| Max Bandwidth(Mbps)| Temp Disk Storage(GiB)|
44+
| --- | --- | --- |---|---|---|
45+
| Standard_NC32ds_xl_RTXPRO6000BSE_v6|32|128|6|25000|256|
46+
| Standard_NC64ds_xl_RTXPRO6000BSE_v6|64|256|6|50000|512|
47+
| Standard_NC128ds_xl_RTXPRO6000BSE_v6|128|512|8|75000|1024|
48+
| Standard_NC256ds_xl_RTXPRO6000BSE_v6|256|1024|8|100000|2048|
49+
| Standard_NC320ds_xl_RTXPRO6000BSE_v6|320|1280|8|200000|2048|
50+
51+
### [Memory Optimized](#tab/sizememoryoptimized)
52+
53+
| Size Name | vCPUs (Qty.) | Memory (GB) |Max NICs (Qty.)| Max Bandwidth(Mbps)| Temp Disk Storage(GiB)|
54+
| --- | --- | --- | --- | --- | --- |
55+
|Standard_NC32mds_xl_RTXPRO6000BSE_v6|32|128|6|25000|256|
56+
|Standard_NC64mds_xl_RTXPRO6000BSE_v6|64|256|6|50000|512|
57+
|Standard_NC128mds_xl_RTXPRO6000BSE_v6|128|512|8|75000|1024|
58+
59+
### [Compute Optimized](#tab/sizecomputeoptimized)
60+
61+
| Size Name | vCPUs (Qty.) | Memory (GB) |Max NICs (Qty.)| Max Bandwidth(Mbps)| Temp Disk Storage(GiB)|
62+
| --- | --- | --- | --- | --- | --- |
63+
|Standard_NC16lds_xl_RTXPRO6000BSE_v6|16|64|4|25000|256|
64+
|Standard_NC32lds_xl_RTXPRO6000BSE_v6|32|128|6|25000|256|
65+
|Standard_NC64lds_xl_RTXPRO6000BSE_v6|64|256|6|50000|512|
66+
|Standard_NC128lds_xl_RTXPRO6000BSE_v6|128|512|8|75000|1024|
67+
|Standard_NC256lds_xl_RTXPRO6000BSE_v6|256|1024|8|100000|2048|
68+
|Standard_NC320lds_xl_RTXPRO6000BSE_v6|320|1280|8|200000|2048|
69+
70+
71+
#### VM Basics resources
72+
- [Check vCPU quotas](../../../virtual-machines/quotas.md)
73+
74+
75+
## Storage Notes
76+
- Temp disk speed varies between Random Read (RR) and Random Write (RW). RR is typically faster.
77+
- Capacity is shown in GiB (1024³ bytes). When comparing to GB (1000³ bytes), GiB values may appear smaller. For example, 1023 GiB = 1098.4 GB.
78+
- Disk throughput is measured in IOPS and MBps (MBps = 10⁶ bytes/sec).
79+
- For optimal storage performance, see [Virtual machine and disk performance](../../../virtual-machines/disks-performance.md).
80+
81+
## Networking Notes
82+
83+
- Expected bandwidth is the maximum aggregated bandwidth per VM type across all NICs. For more information, see [Virtual machine network bandwidth](/azure/virtual-network/virtual-machine-network-throughput).
84+
- Upper limits are guidelines, not guarantees. Actual performance depends on network congestion, application load, and settings. To optimizing network throughput, see [Optimize network throughput for Azure virtual machines](/azure/virtual-network/virtual-network-optimize-network-bandwidth).
85+
- For bandwidth testing, see [Bandwidth/Throughput testing (NTTTCP)](/azure/virtual-network/virtual-network-bandwidth-testing).
86+
87+
88+
[!INCLUDE [sizes-footer](../includes/sizes-footer.md)]

0 commit comments

Comments
 (0)