QUASAR Ryzen AI Max 16" Mobile Workstation

Overview

The unified-memory advantage, in a machine you can carry. A 16-inch mobile workstation on the Ryzen AI Max platform — up to 128 GB of unified memory across four channels, a 50 TOPS NPU and Navi 3.5 graphics with up to 20 WGP — so the model size you can run is set by system memory, not by a soldered VRAM budget. Available on volume order from 100 units.

Key highlights

• 16″ 2560 × 1600, 165 Hz, 100% sRGB, 500 nit — OLED option available.
• Up to 128 GB LPDDR5X across 4 channels at 8000 MT/s — user-assignable to graphics.
• 50 TOPS NPU with Navi 3.5 graphics, up to 20 WGP.
• 16-core AMD Ryzen AI Max+ at an 85 W TBP.
• 99.9 Wh battery — the maximum permitted in aircraft cabin baggage.
• 20.04 mm thick — a genuine mobile workstation, not a desktop replacement.
• Volume order: minimum 100 units. Institutional, tender and fleet supply.

AI workload fit

• Local inference for engineers and analysts who travel.
• RAG over confidential material with no network dependency.
• Agentic AI and application development away from the office.
• Generative AI and creative production on location.
• NLP & speech capture and processing in the field.
• Institutional fleets — teaching labs, field teams, tender-supplied deployments.

AI workload positioning

A conventional AI laptop is limited by soldered VRAM: the discrete GPU has what it has, and a model that does not fit does not run. The unified-memory architecture removes that ceiling, which is why this platform runs model sizes ordinary mobile hardware cannot. It is still a mobile machine — an 85 W TBP in a 20 mm chassis will thermally limit before a desk-side unit, and sustained multi-hour training is not its job. For fleet deployment where staff must run real models offline, that trade is usually the right one. Supplied on volume orders from 100 units.

Industry use cases

• Enterprise & GCCs: fleet refresh for applied-AI, consulting and field engineering teams.
• Research & education: teaching-lab and student-issue fleets running real models offline.
• Public sector & sovereign: tender-supplied mobile fleets with on-device AI, GeM-available.
• BFSI: field and audit staff working on confidential material without connectivity.
• Healthcare: mobile clinical documentation across sites.

Performance & how to be sure

Judge a mobile machine on sustained throughput and thermals, never peak — an 85 W platform in a 20 mm chassis behaves differently in hour two. RDP will run your model on a sample unit before a fleet order. 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

QUASAR performance tier in AI Workstations. Desk-side equivalents: the CARINA 1L/2L compact units, the QUASAR 4L Desktop and the RDP Tower Workstation — the same unified-memory architecture without the mobile thermal ceiling. Above: discrete-GPU RDP AI Workstations.

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

99.9 Wh battery — the maximum permitted in aircraft cabin baggage — with USB-C/DC charging. 85 W platform TBP; expect thermal limiting under sustained load, as with any 20 mm chassis. 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. Volume order only — minimum 100 units. Lead time confirmed at quotation against allocation.

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