Frontier supplier enquiry · eight B300 SXM GPUs
Frontier Native 2.3TB
A native 2.3TB HGX B300 platform for tightly coupled frontier workloads.
A quote-only HGX B300 route using eight 288GB SXM GPUs and NVLink/NVSwitch architecture, subject to exact OEM configuration, software support and facility design.
Current quotation and acceptance plan required.
Price, exact parts, compatibility, warranty, delivery and workload results are indicative until confirmed in a written quotation and acceptance record.
Key buying facts
Frontier Native 2.3TB at a glance
- Commercial status
- Quote only current supplier quotation required
- GPU configuration
- 8 × NVIDIA B300 288GB 8 GPUs
- Per-GPU memory
- 288GB physical VRAM per GPU
- Physical GPU total
- 2304GB across 8 GPUs · not automatically pooled
- Physical class
- Rack server SYS-822GS-NB3RT 8U HGX B300 platform
How the memory works: 2,304GB is distributed across eight B300 GPUs connected by HGX NVLink and NVSwitch. The fabric enables high-bandwidth multi-GPU work, but software support and the exact workload still determine usable capacity.
Power planning · Rack server
Approximately 14kW system envelope; exact quoted input pending
Representative intended fit
A named model with a validated HGX B300 runtime
Buyer fit
Start with the reason to own it.
The single-system frontier route for models and training work that genuinely need a tightly coupled accelerator fabric.
Commercial status
Quote only
Final supplier quote required
Includes workload sizing, the configured system, AI software stack, security baseline, burn-in, agreed workload testing, documentation, remote onboarding and 30-day configuration-defect support.
Package figures exclude VAT and cover the stated GPU RIGS deployment scope. Every final order requires a written quotation confirming the specification, availability, delivery, warranty and workload acceptance plan.
A credible fit
- A named model with a validated HGX B300 runtime
- Large-model inference, adaptation or training evaluation
- A buyer with specialist facility and support capability
Choose another route when
- Independent PCIe workers meet the workload
- The decision depends only on aggregate VRAM
- Facility or software compatibility is not yet accepted
System evidence
What is confirmed, calculated and still unknown.
Vendor-documented values, calculations, assumptions and unknowns remain separate. A capability is marked as measured only when a reproducible benchmark exists.
- Commercial status
- quote-only
- Reviewed
- Review again
- Open specification items
- 10
01 / model evidence
Exact checkpoint profiles
0 measured-supported profiles. A named model appears as supported only after the exact checkpoint, runtime, deployment and limits have a reproducible benchmark record.
Current boundary
Kimi K3 is shown only as a calculated native-weight capacity candidate. Aggregate memory arithmetic does not prove a successful load, runtime support, usable context, tokens per second, latency, quality or concurrency.
- Repository state
- Repository state retrieved 2026-07-28; pin an immutable commit before deployment
- Licence
- Licence must be rechecked and recorded before deployment
- Weights
- Official repository MXFP4 checkpoint; MXFP4 weights and MXFP8 activations
- Dated artifact total
- 1,560,936,091,448 bytes across 96 safetensors files
- Documented model context
- Up to 1,048,576 tokens in the model specification
- Runtime
- No versioned runtime, container, driver or CUDA profile validated
- Candidate deployment
- 8 GPUs; tensor and pipeline parallelism not yet fixed
- Tested limits
- Context, input, output, batch and concurrency are all unmeasured
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.
02 / workload acceptance
Beyond language models
Each workload needs its own quality, latency, throughput, stability and resource test. The entries below define what would be measured; they are not performance claims.
01
Language-model inference
Quality pass rate, TTFT, decode and aggregate throughput, latency percentiles, errors, memory, power and temperature at disclosed context, batch and concurrency.
Acceptance definition only. No performance, quality, capacity or suitability result has been measured for this system.
02
Fine-tuning
Completed steps, time, peak memory, loss and held-out evaluation result with exact base checkpoint, method, trainable parameters, dataset, sequence length and batch.
Acceptance definition only. No performance, quality, capacity or suitability result has been measured for this system.
03
Vision and OCR
Field accuracy or character error rate plus latency on a versioned, permission-safe image and document set.
Acceptance definition only. No performance, quality, capacity or suitability result has been measured for this system.
04
Image generation
Latency percentiles, images per second, peak memory, stability and accepted-output rate at exact checkpoint, resolution, steps, sampler, CFG and batch.
Acceptance definition only. No performance, quality, capacity or suitability result has been measured for this system.
05
Video generation
Clip latency, clips per hour, peak memory, stability and accepted-output rate at exact checkpoint, dimensions, frames, frame rate, duration, steps and batch.
Acceptance definition only. No performance, quality, capacity or suitability result has been measured for this system.
03 / configuration
Specification with its certainty attached
The current sources show the basis for each value. The final quotation names the exact supplier, parts, warranty and bill of materials for the ordered system.
| Field | Public value | Evidence state | Qualification |
|---|---|---|---|
| Platform class | Eight-GPU HGX B300 8U partner platform | Vendor documented | Documented by the component or platform vendor; not independently measured by GPU RIGS. the selected supplier is the current supplier route; the exact authorised OEM system, CPU, memory, storage and service configuration remain quote-specific. |
| Chassis class | 8U air-cooled HGX platform | Vendor documented | Documented by the component or platform vendor; not independently measured by GPU RIGS. The the upstream platform OEM system is an upstream platform benchmark, not proof of a GPU RIGS supply agreement. |
| GPU route | 8 × NVIDIA B300 288GB | Vendor documented | Documented by the component or platform vendor; not independently measured by GPU RIGS. Exact board part numbers and serials belong in the final bill of materials. |
| Physical GPU memory total | 2304GB across 8 GPUs | Calculated | Calculated from disclosed inputs; not a measured system result. 2,304GB is distributed across eight B300 GPUs connected by HGX NVLink and NVSwitch. The fabric enables high-bandwidth multi-GPU work, but software support and the exact workload still determine usable capacity. |
| Per-GPU memory | 288GB | Vendor documented | Documented component capacity and the safer first sizing boundary before any supported multi-GPU test. |
| GPU interconnect | HGX B300 NVLink/NVSwitch | Vendor documented | Documented by the component or platform vendor; not independently measured by GPU RIGS. This record applies to an eight-GPU HGX B300 baseboard, not a PCIe add-in-card server. |
| System topology | 8 × 288GB B300 on HGX NVLink/NVSwitch | Vendor documented | Documented by the component or platform vendor; not independently measured by GPU RIGS. |
| CPU | Exact CPU and socket configuration pending supplier BOM | Unknown | Not yet evidenced for the ordered system and must be resolved before acceptance. |
| System memory | Exact system-memory capacity and population pending supplier BOM | Unknown | Not yet evidenced for the ordered system and must be resolved before acceptance. |
| Primary storage | Exact NVMe capacity, model, endurance and layout pending supplier BOM | Unknown | Not yet evidenced for the ordered system and must be resolved before acceptance. |
| Network | Exact network interfaces and fabric pending workload and supplier confirmation | Unknown | Not yet evidenced for the ordered system and must be resolved before acceptance. |
| Cooling | Air-cooled 8U platform | Vendor documented | Documented by the component or platform vendor; not independently measured by GPU RIGS. |
| Commercial status | Quote only | Unknown | No public numeric offer is made. Exact hardware, facility, delivery, warranty and support scope require a written quotation. |
04 / site and facility
The room stays inside the system boundary
Nameplate power, supplier cooling descriptions and aggregate GPU TDP are not a site approval. The exact build and customer facility need written acceptance.
- Input power
- Approximately 14kW system envelope; exact quoted input pending Vendor documented Documented by the component or platform vendor; not independently measured by GPU RIGS. The facility design must use the exact ordered-system specification and measured acceptance result.
- Measured heat output
- Measured wall power and facility heat-rejection requirement pending reference build Unknown Not yet evidenced for the ordered system and must be resolved before acceptance.
- Cooling route
- Air-cooled 8U platform Vendor documented Documented by the component or platform vendor; not independently measured by GPU RIGS.
- Dimensions and handling
- 8U rack server; exact depth and weight pending quoted BOM Vendor documented Documented by the component or platform vendor; not independently measured by GPU RIGS.
- Facility acceptance
- Rack, power, airflow, heat rejection, noise, UPS and service access required Unknown The customer site has not been surveyed. The final ordered configuration and qualified facility design control this decision.
Pre-order site checks
- A suitable 19-inch rack, rail depth, handling route and secure operating location
- A qualified electrical design based on the final PSU population and measured load
- Cooling and heat-rejection capacity for sustained accelerator operation
- Appropriate switching, cabling, remote management and network segmentation
- A named operational owner or contracted support route
05 / delivery and support
A handover boundary, not an implied managed service
The final quotation must name who owns procurement, facility work, acceptance, warranty, remote support, recurring operations and any on-site service.
- Hardware warranty
- Exact whole-system, GPU, DOA, RMA, spares and on-site warranty route pending Unknown Not yet evidenced for the ordered system and must be resolved before acceptance. No supplier or GPU RIGS warranty term is promised by this planning record.
- Availability and lead time
- Build-to-order availability and lead time pending written supplier confirmation Unknown Not yet evidenced for the ordered system and must be resolved before acceptance. This record does not mean the product is stocked or orderable.
- GPU RIGS support baseline
- Remote onboarding and 30-day configuration-defect support Assumption The written quotation and contract confirm this service boundary. It is not a 24-hour managed service or an implied on-site warranty.
Standard service boundary
- Documented workload and site-fit review
- Confirmed bill of materials before procurement
- Configuration, burn-in and agreed smoke-test evidence
- Asset schedule, admin notes and user quick-start material
- Collection or the quoted kerbside or pallet-delivery route
- Remote onboarding and 30-day configuration-defect support
Separate scope or customer responsibility
- Building electrical work, rack, UPS, cooling or structured cabling
- Nationwide on-site installation unless separately quoted
- Migration of customer data, every integration or every application
- Continuous managed operations, security monitoring or a 24-hour support agreement
- Third-party model, API, marketplace or software charges
- A compliance certificate, performance guarantee or income guarantee
06 / sources and review status
Sources and unresolved items
Review dates show evidence freshness, not future availability. A current quote, serialised bill of materials and accepted test record control the order.
- Commercial state
- quote-only
- Reviewed
- 2026-07-28
- Review again
- 2026-08-28
Unresolved before acceptance
- CPU: Exact CPU and socket configuration pending supplier BOM
- System memory: Exact system-memory capacity and population pending supplier BOM
- Primary storage: Exact NVMe capacity, model, endurance and layout pending supplier BOM
- Network: Exact network interfaces and fabric pending workload and supplier confirmation
- Commercial status: Quote only
- Measured heat output: Measured wall power and facility heat-rejection requirement pending reference build
- Facility acceptance: Rack, power, airflow, heat rejection, noise, UPS and service access required
- Hardware warranty: Exact whole-system, GPU, DOA, RMA, spares and on-site warranty route pending
- Availability and lead time: Build-to-order availability and lead time pending written supplier confirmation
- GPU RIGS support baseline: Remote onboarding and 30-day configuration-defect support
-
Product record
Current product specification and commercial status
GPU RIGS
Retrieved 2026-07-28 · reviewed 2026-07-28
The current product record defines the specification and commercial status shown on this page.
-
Product record
Current product specification and commercial status
GPU RIGS
Retrieved 2026-07-28 · reviewed 2026-07-28
The current product record defines the specification and commercial status shown on this page.
-
Supplier reference
Dated supplier configuration evidence
System supplier
Retrieved 2026-07-28 · reviewed 2026-07-28
Dated supplier evidence. Configuration, stock, price and warranty require confirmation in the final quotation.
-
Retrieved 2026-07-28 · reviewed 2026-07-28
Use the linked source to confirm the dated component, platform or checkpoint facts stated above.
-
Supplier reference
Dated supplier configuration evidence
System supplier
Retrieved 2026-07-28 · reviewed 2026-07-28
Dated supplier evidence. Configuration, stock, price and warranty require confirmation in the final quotation.
-
Market comparison
Dated market comparison
Market reference
Retrieved 2026-07-28 · reviewed 2026-07-28
Dated market comparison only; not an exact quotation or proof of product equivalence.
-
Retrieved 2026-07-28 · reviewed 2026-07-28
Use the linked source to confirm the dated component, platform or checkpoint facts stated above.
-
Retrieved 2026-07-28 · reviewed 2026-07-28
Use the linked source to confirm the dated component, platform or checkpoint facts stated above.
-
Retrieved 2026-07-28 · reviewed 2026-07-28
Use the linked source to confirm the dated component, platform or checkpoint facts stated above.
Known limitations
- 2.304TB HBM is a calculated capacity envelope, not proof that the official Kimi K3 checkpoint loads or serves one-million-token context.
- No Kimi K3 throughput, TTFT, concurrency, wall power or quality result has been measured.
- 2.304TB HBM is a calculated capacity envelope, not proof that the official Kimi K3 checkpoint loads or serves one-million-token context.
- No Kimi K3 throughput, TTFT, concurrency, wall power or quality result has been measured.
- Pricing is quote-only.
- Model-fit entries remain candidates until reproducible tests exist.
- Aggregate GPU memory is not one universal memory pool.
- No model, speed, context, concurrency or multi-GPU efficiency promise exists without a controlled fit profile.
- Rack, electrical work, UPS, cooling, cabling, colocation and on-site installation require a separate scope.
Do not buy this route when
- The workload can be served by a smaller PCIe appliance or hosted capacity.
- The site cannot support an 8U, approximately 14kW platform and authorised installation.
- The buyer expects a confirmed Kimi K3 maximum-settings performance promise before testing.
Inspect the evidence behind Frontier Native 2.3TB.
The system view shows the selected hardware reference where available. Technical diagrams explain memory, data boundaries, queues, power and handover. The final bill of materials and workload test confirm the ordered system.
Software and security
The usable product is more than the chassis.
The final stack stays deliberately small. Versions, licences, access and recurring ownership are recorded so the customer is not left with an opaque collection of containers.
Software baseline
- Ubuntu LTS on a recorded operating-system version
- NVIDIA driver, CUDA components and container support validated for the ordered hardware
- Docker Engine and NVIDIA Container Toolkit
- One primary model server selected from Ollama, vLLM, SGLang, TensorRT-LLM or llama.cpp for the accepted workload
- Open WebUI or another reviewed browser interface
- Named authentication, TLS and reverse-proxy approach
- GPU, node and service monitoring with an agreed log-retention period
- Pinned versions, a software bill of materials and a model source and licence record
Security ownership
- GPU RIGS baseline
- Initial operating-system state, named administrator handover, host firewall baseline, agreed access route, secrets transfer and documented update state.
- Customer or contracted operator
- User lifecycle, network and VPN policy, backups, monitoring review, patch approval, incident response, data governance and lawful use.
- Shared before acceptance
- Model and software licence checks, retention and logging choices, recovery test, acceptance criteria and a named owner for every recurring task.
Local infrastructure can reduce disclosure to external AI APIs. It does not automatically make the service secure, accurate, confidential or UK GDPR compliant.
Testing and acceptance
The evidence pack is part of the machine.
Performance is confirmed against the accepted workload, exact build and disclosed test conditions. No throughput, latency or quality figure is claimed before that test.
- 01
Record the final bill of materials, serial numbers and firmware versions.
- 02
Run at least 24 hours of GPU, CPU, memory and storage stress testing.
- 03
Capture temperature, fan, error, health and wall-power evidence under the agreed load.
- 04
Test cold boot, restart and the available remote-management route.
- 05
Check drive health, network throughput and the container and GPU runtime.
- 06
Run model and workload smoke tests against the written acceptance set.
- 07
Record any measured speed only with the model, quantisation, context, concurrency and runtime disclosed.
- 08
Test an agreed fault or recovery route and provide the resulting handover record.
What is not claimed today
No fixed users, tokens per second, latency, model size, accuracy, availability, savings or marketplace contribution is stated without the missing configuration and test conditions.
See how systems are testedCommercial reality
Tax and spare capacity are supporting questions.
Neither belongs in a guaranteed saving or payback claim. The purchase must stand on the accepted workload, control case and operating plan.
Finance, VAT and capital allowances
- The displayed figure is for a complete GPU RIGS private AI deployment, not unconfigured hardware. The final written quotation confirms the exact specification, delivery, warranty and accepted workload scope.
- Prices exclude VAT. VAT recovery depends on the buyer, its taxable activities and the normal evidence rules.
- Qualifying equipment may be plant and machinery for capital-allowance purposes. The buyer's accountant decides eligibility and timing.
- A third-party lease or hire-purchase route may be explored after partner validation and credit approval. GPU RIGS is not presented as a lender.
- There is no generic capital-gains advantage and no automatic research and development relief because the equipment supports AI.
Optional idle capacity
- Marketplace mode is off by default and is excluded from the purchase case.
- A separate environment, no customer data mounts, network controls and a local kill switch would be required.
- The customer, insurer, supplier warranty and marketplace terms must permit the intended use.
- Vast.ai, Render, Golem and direct batch work do not guarantee acceptance, demand, rate or income.
- Any dated estimate must identify its source date; a pilot must report achieved utilisation, fees, electricity, cooling, faults and operator time.
Limits and alternatives
A good specification leaves room for “no”.
The fit check can recommend a smaller system, hosted service, hybrid route, custom build or no purchase. That is preferable to making this package carry a workload it has not proved.
Package boundaries
- Aggregate GPU memory is not one universal memory pool.
- No model, speed, context, concurrency or multi-GPU efficiency promise exists without a controlled fit profile.
- Rack, electrical work, UPS, cooling, cabling, colocation and on-site installation require a separate scope.
- 2.304TB HBM is a calculated capacity envelope, not proof that the official Kimi K3 checkpoint loads or serves one-million-token context.
- No Kimi K3 throughput, TTFT, concurrency, wall power or quality result has been measured.
- Pricing is quote-only.
- Model-fit entries remain candidates until reproducible tests exist.
- Aggregate GPU memory is not one universal memory pool.
- No model, speed, context, concurrency or multi-GPU efficiency promise exists without a controlled fit profile.
- Rack, electrical work, UPS, cooling, cabling, colocation and on-site installation require a separate scope.
Choose the smaller system when it meets the accepted workload and resilience requirement.
Consider this route Custom specificationUse when storage, network, resilience, colocation or service design differs from the reference route.
Consider this route Hosted or hybrid AIMay be preferable for bursty demand or where the organisation cannot own the facility and operating burden.
Consider this routeQuestions answered
Frontier Native 2.3TB questions that affect the order
The written quotation and acceptance plan confirm any price, specification, warranty or workload assumption discussed below.
Does Frontier Native 2.3TB provide 2304GB as one memory pool?
Only a single-GPU system provides its stated GPU memory on one card. Multi-GPU totals are aggregate physical capacity; usable sharding depends on the exact model, runtime and topology.
Which models are supported?
Only models with a reproducible fit profile are listed as supported. Capacity candidates are labelled separately; a memory calculation alone is not a support claim.
Is the displayed price final?
No. An indicative price is a transparent planning value based on dated inputs. Quote-only platforms and the final order require a current supplier quote, accepted bill of materials and delivery scope.
Can spare capacity earn income?
It may be evaluated as an optional isolated secondary use. Marketplace acceptance, utilisation, rates, fees, energy and income can change and are never guaranteed or included in the purchase case.
Prepare the next decision
Specify the work before the parts.
Record the workload, data boundary, users, site and acceptance test. No confidential documents or credentials are needed for the first brief.
Package figures exclude VAT and cover the stated GPU RIGS deployment scope. Every final order requires a written quotation confirming the specification, availability, delivery, warranty and workload acceptance plan.