GPU Servers UK
Menu
Servers

SME workstations

Team 32Company 64Studio 96Studio 192

Enterprise & frontier

Value Rack 128Value Rack 256Enterprise 384Enterprise 768H200 1.1TBFrontier Native 2.3TBFrontier Rack 20TB
Compare serversFilter all serversCustom specification
Solutions All workloadsPrivate AI serversPrivate chat & RAGAI codingRendering & batchFor legal teamsFor engineering
Why private AI Why own capacity?Private vs cloudSecurity & data controlOpen-source softwareFinance & tax context
Crypto & blockchain Crypto & blockchain overviewGPU mining rigsMining configuration serviceBlockchain infrastructureMining ROI calculatorGPU-mineable tokensMining exit strategiesMining FAQs
Learn Buyer guidesModel compatibilityCompare serversServer sizing toolTCO calculatorAI ownership calculatorElectricity calculatorHow systems are testedPrivate AI questions
About Plan your server

Model and hardware fit

Match the exact checkpoint, not just the model family.

Each fit record names the checkpoint, weight format, dated artefact inventory and compatible hardware state. “Not evaluated” does not mean unsupported, and aggregate memory alone does not mean compatible.

Browse checkpoint records Compare GPU servers
Diagram showing an approved request, a local service, an approved store and a policy-controlled data path
Diagram showing an approved request, a local service, an approved store and a policy-controlled data path
A private deployment starts with the permitted data path, access policy and logging boundary. GPU Servers technical illustration.
A private deployment starts with the permitted data path, access policy and logging boundary.
1exact checkpoint registered
0measured system matches
2calculated capacity candidates

Named checkpoints

Registered model checkpoints

Each record identifies an exact repository revision and review date. Similarly named checkpoints, unofficial conversions and unlisted model families have not been evaluated.

Moonshot AI · Kimi K3

moonshotai/Kimi-K3

Repository state retrieved 2026-07-28; pin an immutable commit before deployment

Review checkpoint fit
Parameters
2.8 trillion total parameters; 104 billion active parameters
Official artefact inventory
1,560,936,091,448 bytes across 96 safetensors files
Native format
Native MXFP4 weights and MXFP8 activations
Model specification context
Up to 1,048,576 tokens in the model specification
System Class GPU memory Evidence state What the record proves
Team 32 SME workstations 32GB aggregate Not evaluated No checkpoint-to-system fit test is recorded. This is neither a support promise nor a rejection.
Company 64 SME workstations 64GB aggregate Not evaluated No checkpoint-to-system fit test is recorded. This is neither a support promise nor a rejection.
Studio 96 SME workstations 96GB aggregate Not evaluated No checkpoint-to-system fit test is recorded. This is neither a support promise nor a rejection.
Studio 192 SME workstations 192GB aggregate Not evaluated No checkpoint-to-system fit test is recorded. This is neither a support promise nor a rejection.
Value Rack 128 Enterprise PCIe racks 128GB aggregate Not evaluated No checkpoint-to-system fit test is recorded. This is neither a support promise nor a rejection.
Value Rack 256 Enterprise PCIe racks 256GB aggregate Not evaluated No checkpoint-to-system fit test is recorded. This is neither a support promise nor a rejection.
Enterprise 384 Enterprise PCIe racks 384GB aggregate Not evaluated No checkpoint-to-system fit test is recorded. This is neither a support promise nor a rejection.
Enterprise 768 Enterprise PCIe racks 768GB aggregate Not evaluated No checkpoint-to-system fit test is recorded. This is neither a support promise nor a rejection.
H200 1.1TB Enterprise PCIe racks 1,128GB aggregate Not evaluated No checkpoint-to-system fit test is recorded. This is neither a support promise nor a rejection.
Frontier Native 2.3TB Frontier partner platforms 2,304GB aggregate Calculated capacity candidate HGX B300's documented 2.30TB aggregate HBM3e exceeds the dated 1.5609TB repository weight total. This arithmetic establishes only a memory-capacity candidate, not a successful load, usable context, throughput, latency or concurrency.
Frontier Rack 20TB Frontier partner platforms 20,736GB aggregate Calculated capacity candidate GB300 NVL72's documented 20TB aggregate GPU memory is a capacity candidate for this checkpoint. Its commercial purpose is rack-scale throughput and concurrency, neither of which is measured here; checkpoint fit alone does not justify the platform.

Aggregate GPU memory is an inventory value. It is not automatically a single pooled-memory address space, and it does not prove a successful model load.

Evidence key

Four states, four different conclusions.

Measured support
An exact build and runtime passed a recorded benchmark and acceptance gate.
Vendor-documented candidate
Primary documentation supports the candidate, but GPU RIGS has not measured it.
Calculated capacity candidate
Disclosed arithmetic clears one capacity check only; loading and performance remain unproved.
Not evaluated
No checkpoint-to-system fit test is recorded. It is neither a support promise nor a rejection.

Checkpoint fit connects software requirements to physical hardware

Memory, data boundaries, service management and handover each affect deployment suitability. Concept diagrams do not replace benchmark logs from the exact build.

Diagram showing an approved request, a local service, an approved store and a policy-controlled data path
Diagram showing an approved request, a local service, an approved store and a policy-controlled data path
A private deployment starts with the permitted data path, access policy and logging boundary. GPU Servers technical illustration.
A private deployment starts with the permitted data path, access policy and logging boundary. GPU Servers technical illustration.
GPU server remote management dashboard with system status, access logs and sensor monitoring panels
GPU server remote management dashboard with system status, access logs and sensor monitoring panels
Supplier screenshot of the platform management interface. The final management features and access policy depend on the ordered system. OEM supplier reference image.
Supplier screenshot of the platform management interface. The final management features and access policy depend on the ordered system. OEM supplier reference image.
Diagram showing approved documents moving through a searchable index to an answer with a source citation
Diagram showing approved documents moving through a searchable index to an answer with a source citation
A retrieval workflow should connect each useful answer to approved source material and defined refusal behaviour. GPU Servers technical illustration.
A retrieval workflow should connect each useful answer to approved source material and defined refusal behaviour. GPU Servers technical illustration.
Diagram of an evidence pack containing an asset schedule, burn-in record, health readings, workload test and admin guide
Diagram of an evidence pack containing an asset schedule, burn-in record, health readings, workload test and admin guide
A credible handover records the supplied assets, checks, operating evidence, instructions and unresolved items. GPU Servers technical illustration.
A credible handover records the supplied assets, checks, operating evidence, instructions and unresolved items. GPU Servers technical illustration.