Alexios Bluff Mara × Illinois State University
Research Collaboration · Cardinal & Code
Research posture RTX 5090 → ACCESS-CI HPC Open-source · Local-first

Hardware-flexible research,
built where cardinal meets code.

The lab's research posture in three words: hardware-flexible, open-source, local-first. Same code path across a single Blackwell card, a Cloud Run L4 burst node, and an HPC partition.

From an RTX 5090 to a national HPC partition

The baseline workstation is a single RTX 5090 — 32 GB GDDR7, Blackwell sm_120 — sitting under a desk in Chicago. That's where the model graphs are tuned and the inference pipelines validated. From there, the same code path scales out two ways:

  • Burst capacity on Google Cloud Run L4 GPU nodes — about $0.70/hour, scale-to-zero when idle, used as a fallback when the local card is busy.
  • National HPC capacity via ACCESS-CI, the NSF-funded successor to XSEDE, accessed through partner institutions including UIUC. A100 / H100 partitions handle full-resolution prediction grids and large batched inference jobs.
  • Air-gapped HPC deployment is supported. Cortex ships a deployable container with model weights baked in — operators can docker load on a fresh node and have the pipeline live in minutes, useful where outbound HuggingFace downloads aren't permitted.

Offline-capable by design

Academic networks and HPC partitions often block outbound traffic. The lab's projects are built to run with no internet connection after first install: model weights cached locally, inference and narration both on-device, no cloud round-trips in the hot path. Mercury takes this further — its production runtime never leaves the operator's hardware. Cortex's local mode is identical in posture; the hosted demo at cortex.redteamkitchen.com is a convenience layer, not a requirement.

Open-source posture

Code: Apache-2.0 (Cortex) and MIT (Mercury). Every commit, every issue, every model config is public on the AlexiosBluffMara GitHub organization. Third-party model weights ship under their respective licenses — TRIBE v2 under CC-BY-NC 4.0 (Meta), Gemma 4 under the Gemma Terms of Use (Google) — and are documented in each project's NOTICE file.

ISU departments and facilities

The academic homes the research draws from. None of these endorse the lab's work; they are listed because they are the units the research intersects with.

Department
School of Information Technology
illinoisstate.edu/departments/sit
Department
Department of Psychology
psychology.illinoisstate.edu
Department
School of Biological Sciences
bio.illinoisstate.edu
Facility
Milner Library
library.illinoisstate.edu
Facility
College of Applied Science & Technology
cast.illinoisstate.edu
Compute
ACCESS-CI
access-ci.org
Research conducted in association with Illinois State University, research collaboration · Bloomington–Normal, IL · ABM in Chicago, IL.
Alexios Bluff Mara LLC · 2026