CARINA Ryzen AI Max 23.8" AI All-in-One

Overview

One cable, one device, a large model running locally. A 23.8-inch FHD all-in-one with the Ryzen AI Max platform behind the panel and up to 128 GB of unified memory — no tower, no adapter, nothing under the desk. At a 55 W platform envelope it runs quietly in shared and patient-facing spaces where a workstation would be intrusive.

Key highlights

• 23.8″ FHD 16:9 display with the AI platform integrated behind it.
• Up to 128 GB LPDDR5X-8000 unified memory — large local models, no discrete VRAM limit.
• 50 TOPS NPU — a genuine AI PC, not a thin client with a badge.
• 55 W platform envelope — quiet enough for clinics, branches and shared desks.
• 2× M.2 NVMe PCIe 4.0 ×4 for datasets and model weights on-device.
• Liftable or fixed stand; 2.5GbE, USB 3.2 Gen2, USB-C option, HDMI, audio.
• Single power lead — the lowest-clutter way to put local AI on a desk.

AI workload fit

• Local inference at a shared or public-facing desk.
• RAG over local documents in a branch, clinic or office.
• NLP & speech — transcription, dictation and summarisation.
• Agentic AI assistants running on the device rather than in a cloud.
• Generative AI for document and content production.
• Kiosk, reception and consultation-room deployments needing on-device AI.

AI workload positioning

The all-in-one exists for placement, not peak performance. At 55 W it deliberately trades the headroom of the 2 L and 4 L units for silence, a single cable and a small footprint — which is what makes it viable in a consulting room, a bank branch or a shared workspace where a tower is unwelcome. Expect the memory capacity of the family and a lower sustained ceiling; if throughput matters more than placement, choose the 4 L desktop instead.

Industry use cases

• Healthcare: consultation-room documentation and coding assistance, on-premises under DPDP.
• BFSI: branch-level assistants working on customer data without leaving the network.
• Enterprise & GCCs: shared-desk and hot-desk AI without a tower per seat.
• Public sector & sovereign: citizen-facing counters with on-device AI.
• Research & education: lab and classroom machines with a clean single-cable install.

Performance & how to be sure

The 55 W envelope is the defining constraint — memory capacity matches the rest of the family, sustained throughput does not, and we would rather state that than let it surprise you. Rather than quote a tokens/sec figure that will not match your workload, RDP offers a “benchmark your model” session: bring the model, precision and context length you actually intend to run, and we will validate it on this exact configuration before you commit.

Series & upgrade path

CARINA entry tier. Beside: the 1L Mini AI Workstation where a separate display is preferred. Above: the 2L Compact, the 2L Liquid-Cooled and the 4L Desktop Workstation as thermal headroom becomes the constraint.

On-prem vs cloud (TCO)

For sustained daily AI work this configuration removes per-GPU-hour billing, queueing for scarce instances, and egress charges on your own data — and keeps everything on-premises for DPDP and data-residency obligations. Cloud still wins for burst capacity and one-off very large training runs; on-prem wins on sustained utilisation, control and predictable INR capital cost. We model the crossover with your actual usage rather than assert it.

Software & day-one readiness

Ships with Windows 11 or Ubuntu and the AMD AI stack — ROCm, DirectML and ONNX Runtime — with local model runtimes (LM Studio, Ollama, llama.cpp) validated before dispatch. The GPU draws from the same unified pool as the CPU, so you assign memory to the model rather than shopping for a card with enough VRAM. Migration from a CUDA workflow is a real exercise and RDP scopes it honestly rather than calling it a drop-in swap.

Power, thermal & acoustics

55 W platform envelope, DC jack, single mains lead. Air-cooled and quiet by design — chosen specifically for occupied, patient-facing and public-facing rooms. Exact wattage, BTU and dB(A) figures come from RDP bench measurement rather than estimates — ask for the site-readiness sheet with your quote.

Deployment, warranty & support

Built to order by RDP Technologies. Supplied with GST invoice, pan-India onsite support, and availability through GeM for public-sector procurement. Built to order — typically 5–7 weeks.

Why RDP

RDP Technologies is a Make-in-India OEM with 14+ years and 300,000+ units shipped, supplying AI infrastructure from desk-side systems to rack-scale AI factories — with predictable INR pricing, GST invoicing and pan-India onsite service.

Buy with confidence

Use Request a Quote to reach an RDP solution architect for sizing, a benchmark-your-model session, financing options and a delivery plan. No obligation.

Specifications