BLOG · GUIDE · · UPDATED

NVIDIA RTX PRO 6000 Blackwell Max-Q in VMs: passthrough, MIG and why there is no vGPU

Eurokommerz, Vienna, since 2006: Private AI/ML · IT Managed Services · Enterprise Training · AI Hardware & Software

IN BRIEF
  • NVIDIA's list of GPUs supported by vGPU software (2 October 2026) and its hypervisor matrices name the RTX PRO 6000 Blackwell Server Edition, not the Max-Q Workstation Edition, so the Max-Q has no vGPU profiles
  • A Max-Q can still go to one VM as a whole card by PCIe passthrough; NVIDIA's MIG guide supports MIG inside Linux guests in passthrough, so one VM can split its card into up to four 24 GB instances
  • MIG instances of one card cannot go to separate VMs without vGPU: NVIDIA describes MIG-backed vGPU as the way to run several VMs on one MIG GPU
  • Users have reported reset problems in passthrough after a guest shuts down; NVIDIA documents none for this card as of 5 November 2026, so test VM restarts and resets before production, above all with several cards
  • For several VMs per card, vSphere with vGPU or NVIDIA AI Enterprise support, take the RTX PRO 6000 Blackwell Server Edition, which NVIDIA supports from vGPU 19.0

Supplied by Eurokommerz: NVIDIA RTX PRO 6000 Blackwell  Check price and availability →

What NVIDIA supports for the Max-Q in virtual machines

The NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition can run in a virtual machine only as a whole card passed through to one guest. NVIDIA does not list it for vGPU, so it has no time-sliced or MIG-backed vGPU profiles; NVIDIA's MIG guide does let a Linux guest split a passed-through card into MIG instances for its own containers. For several VMs per card, vGPU on vSphere or NVIDIA AI Enterprise support, the RTX PRO 6000 Blackwell Server Edition is the edition NVIDIA lists.

FEATUREMAX-QSERVER EDITION
NVIDIA vGPU softwarenot listedfrom release 19.0
vGPU hypervisor matricesnot listedlisted
MIG on bare metalup to 4 instancesup to 4 instances
MIG in a passthrough guestMIG guide: supportedMIG guide: supported
MIG slices for several VMsno, needs vGPUyes, MIG-backed vGPU
NVIDIA AI Enterprise 8.2not listedlisted
Cooling, board powerblower, 300 Wpassive, up to 600 W

NVIDIA list of GPUs supported by vGPU software (updated 2 October 2026), NVIDIA vGPU product support matrices for vSphere, RHEL with KVM and Ubuntu (29 September 2026), NVIDIA MIG user guide (13 October 2026), NVIDIA AI Enterprise 8.2 support matrix, NVIDIA RTX PRO 6000 family page; all read 24 October 2026.

Server makers draw the same line. Lenovo's product guide LP2364 for the Max-Q, updated on 8 May 2026, gives "vGPU software support" as "No support" and records that Lenovo "removed the NVIDIA vGPU Software part numbers since the GPU does not support vGPUs". It lists the card as an option for two servers only, the ThinkSystem SR655 V3 and SR665 V3. The three editions side by side are in our comparison of the RTX PRO 6000 Server, Workstation and Max-Q editions.

Whole-card passthrough on KVM and Proxmox

With passthrough, the hypervisor hands the whole PCIe device to one VM, on KVM through the VFIO driver, and the guest loads the normal NVIDIA driver as if it ran on bare metal. The guest sees all 96 GB, the full compute and, if they are switched on, the four DisplayPort outputs. Nothing is shared: one card, one VM, and a host with four Max-Q cards runs at most four GPU VMs, or fewer if one VM takes two or four cards for a model split across them.

NVIDIA's own documents say little about this case. The release notes of its R595 data-centre driver (version 4.0, driver 595.112.07 of 22 October 2026) list "NVIDIA RTX 6000 PRO", without an edition, among the GPUs supported for device passthrough, on hypervisors that include VMware vSphere and Red Hat Enterprise Linux 9 with KVM; Proxmox VE is not in that list. The MIG user guide's "Supported Configurations" page lists "GPU pass-through virtualization to Linux guests on top of supported hypervisors" for MIG-capable GPUs, and its GPU table names the "RTX PRO 6000 Blackwell Max-Q Workstation Edition" with four instances. In practice, Max-Q passthrough relies on the hypervisor's own PCIe passthrough, without an NVIDIA hypervisor matrix that names this edition.

Three practical points follow from the sources further down.

  • One VM per card, sized for its model. A VM that serves a 70B model in FP8 on one card needs the whole 96 GB anyway. By our users-per-card rule a card leaves 83.0 GiB for weights and cache (0.9 × 95.6 GiB − 3 GiB), which holds 12 conversations of 8,192 tokens with Llama 3.3 70B in FP8.
  • Several cards in one VM. A VM with two or four cards for tensor parallelism loses part of the peer-to-peer path. NVIDIA's NCCL troubleshooting guide states that "Virtual machines require ACS to function, hence disabling ACS is not an option", and ACS can send GPU-to-GPU traffic through the processor. Our guide to P2P, IOMMU and ACS on Linux shows how to measure what is left.
  • No live migration. A passed-through card is tied to its host, so maintenance on the host means shutting the VM down. On vSphere, Broadcom's knowledge base article 428701 allows snapshots of passthrough VMs only when they are powered off.

Which edition and how many cards fit your virtual machines depends on the hypervisor and the number of VMs per card; send us your hypervisor and the VMs you plan, and our team replies with the edition and a configuration.

Resets after guest shutdown in Proxmox and KVM

When a guest shuts down, the host's VFIO driver resets the card and holds it, idle, until the next VM starts. Users have reported reset problems in this cycle in passthrough. NVIDIA documents none for this card as of 5 November 2026: its R595 driver release notes of 22 October 2026 list no passthrough, FLR or reset issue, and we found no NVIDIA or Proxmox document that describes a fix.

What to test before going live

On a new Max-Q host, test the start and shutdown cycle before going live: start and shut down every VM, with the cards in use, many times in a row, and watch the host log for FLR and D3cold messages. A host that survives that cycle at acceptance still needs the same check after each kernel or driver update. Our guide to burn-in and acceptance testing describes the rest of the acceptance run.

MIG on the host or inside the guest

The Max-Q supports MIG with up to four instances: NVIDIA's datasheet gives 4 × 24 GB, 2 × 48 GB or 1 × 96 GB. As our MIG setup guide for RTX PRO Blackwell explains, MIG on the RTX PRO 6000 needs Linux, driver 575.51.03 or later, current card firmware and the card switched to compute mode with NVIDIA's DisplayModeSelector, which turns the display outputs off.

There are two places to use it.

  1. On a bare-metal Linux host. The host splits each card into instances and gives them to containers or Kubernetes pods, which the MIG guide lists as "Bare-metal, including containers and MIG with Kubernetes". This is the way to give four teams a 24 GB slice each without virtual machines. Our article on GPU sharing in Kubernetes covers the scheduling.
  2. Inside one passthrough VM. NVIDIA's MIG guide states that under Linux guests on supported hypervisors, with the GPU in passthrough, the same workflows, tools and profiles as on bare metal can be used. The VM owns the whole card and splits it for its own workloads.

What MIG cannot do on the Max-Q is put its instances into different virtual machines. The MIG guide's virtualisation page names MIG-backed vGPU as the way to run several VMs in parallel on one MIG GPU, and the Max-Q has no vGPU support. A VM per 24 GB slice, as on the Server Edition, needs vGPU. The four instances and their engines are listed in our guide to RTX PRO 6000 MIG profiles.

When you need the RTX PRO 6000 Server Edition

The Max-Q is a workstation card. NVIDIA rates it for "up to four GPUs in a single system" and describes the family's Server Edition as "designed for multi-GPU server deployments requiring passive cooling". For virtual machines, five requirements point to the Server Edition.

  • Several VMs per card. NVIDIA lists time-sliced and MIG-backed vGPU types for the Server Edition, up to four MIG slices of 24 GB and 12 compute VMs of 8 GB per card, as our guide to RTX PRO 6000 Server Edition vGPU profiles shows.
  • VMware vSphere with vGPU. NVIDIA's vSphere matrix lists the Server Edition for VCF 9.1, VCF 9.0.1 or later and ESXi 8.0 Update 3g or later; the Max-Q is not in it.
  • NVIDIA AI Enterprise support. The 8.2 support matrix lists the RTX PRO 6000 Blackwell Server Edition and the RTX PRO 4500 Blackwell Server Edition among its discrete Blackwell GPUs, in servers on NVIDIA's certified-systems list, and does not list the Max-Q.
  • A long support window. The Server Edition is on vGPU 19, the long-term branch NVIDIA supports until July 2028.
  • A rack server in continuous operation. For continuous operation in a rack we recommend the Server Edition. Many server makers do not list the Max-Q for their GPU servers: in a dense chassis each blower's intake sits against the next card, and the airflow is designed for passive cards; our checklist for the Max-Q in a rack server goes through the cases where a maker does list it.

The Max-Q stays a good fit where one workstation or one VM owns each card: a deskside machine with two to four cards for a team, a lab host where each researcher's VM gets a whole card, or a bare-metal Linux box that shares cards by MIG among containers. Our pages on two Max-Q cards in a workstation and four in one workstation size those builds.

We supply the RTX PRO 6000 in all three editions, as cards or in workstations and servers built to order, and the Server Edition with vGPU or NVIDIA AI Enterprise licences on the same quote. Tell us how many VMs share each card, and we say which edition fits before you order.

Licences for passthrough, MIG and vGPU

Licensing follows the edition. The Max-Q has no vGPU profiles, so vGPU licences do not apply to its virtual machines. On the Server Edition, NVIDIA's client licensing guide maps Q-series vGPUs to RTX vWS, B-series to vPC or vWS and A-series to vApps, and states that "In GPU pass-through mode on Linux, a physical GPU requires a vWS license". Compute vGPUs need NVIDIA AI Enterprise, which NVIDIA licenses "on a per-GPU basis". Our page on NVIDIA AI Enterprise and vGPU licences lists the editions we supply.

FAQ

Does the RTX PRO 6000 Max-Q support vGPU?
No. NVIDIA's list of GPUs supported by vGPU software, updated on 2 October 2026, names the RTX PRO 6000 Blackwell Server Edition and its liquid-cooled version, not the Max-Q. Lenovo removed the vGPU part numbers from its Max-Q option because the card does not support vGPUs.
Can I pass an RTX PRO 6000 Max-Q through to a VM on Proxmox or KVM?
Yes, as a whole card to one VM through VFIO. NVIDIA publishes no hypervisor matrix for this edition, and its R595 driver notes, which list the RTX PRO 6000 for passthrough without an edition, do not name Proxmox VE. Test VM restarts and resets before production.
Can I use MIG on the RTX PRO 6000 Max-Q in a virtual machine?
Inside one Linux VM that owns the whole card by passthrough, yes: NVIDIA's MIG guide supports the same MIG workflows in passthrough guests as on bare metal. Giving each MIG instance to a different VM needs MIG-backed vGPU, which the Max-Q does not have.
How do I fix the RTX PRO 6000 passthrough reset bug in Proxmox?
Users have reported reset problems in passthrough, but NVIDIA documents none for this card as of 5 November 2026, and we found no fix documented by NVIDIA or Proxmox. Test VM restarts and resets on the delivered host before production and after each kernel or driver update; for several VMs per card, NVIDIA supports the RTX PRO 6000 Server Edition with vGPU.
Max-Q or Server Edition for virtual machines?
The Server Edition, if several VMs share a card, if you run vSphere with vGPU, or if you need NVIDIA AI Enterprise support. The Max-Q fits where each VM or workstation owns whole cards, or where a bare-metal Linux host shares cards among containers with MIG.
How many VMs can one RTX PRO 6000 Max-Q serve?
One VM per card by passthrough. Inside that VM, MIG splits the card into up to four 24 GB instances for containers. The Server Edition with vGPU takes up to 12 compute VMs of 8 GB or four isolated VMs of 24 GB per card.

We supply the RTX PRO 6000 Max-Q and Server Edition as cards or in systems built to order, with vGPU licences where the Server Edition needs them. Describe your task in a few sentences and our team will help. We reply within one business day.

Talk to an expert
Talk to an expert

We reply within one business day

By sending this form you agree that we process your details to answer your enquiry; see our privacy policy.

request@eurokommerz.at
Jordangasse 7, 1010 Vienna