AGmind Request a scope

AGmind Systems Lab

Local AI, qualified as a system.

Exact hardware and software versions, model artifacts, frozen workloads, measured operating limits, known failures and reproducible deployment evidence.

A device spec says how much memory a box has. A demo benchmark gives one number. Neither answers whether your exact model and runtime can be operated under your real load. AGmind Systems Lab tests the whole system and limits every conclusion to what was actually run.

Reviewed configurations

No published configurations yet

The first cards ship with the Strix Halo Runtime Qualification v1 flagship. Cards appear here only after runs pass methodology v1 validation — nothing is backfilled from legacy data.

What AGmind qualifies

Deliberately not offered yet

These become products only after paid demand proves they should exist:

  • AGmind Reference Stack after demand gate
  • Release Revalidation Channel after demand gate
  • BenchOps after demand gate

Failures and corrections

Negative results are first-class output here: a paid test that refutes a claim is published (in independent mode) with the same rigor as a pass. The errata log records every correction to published results.

Read the errata policy →

Methodology

Every qualification follows the same controlled process: an agreed question, frozen versions and workload, preregistered metrics and exclusion rules, preserved failures and invalid runs, a scoped conclusion, and a reproducible evidence bundle. Repeats are mandatory for headline numbers; failed requests stay in the denominator.

Read the methodology →

Workload library

Qualification runs against fixed, versioned workloads — not ad-hoc prompts. All v1 workloads are drafts until their corpora, hashes and acceptance checks are frozen.

Lab hardware

The stands that actually exist in the lab, with their limits stated. No result generalizes beyond the tested unit and versions.

Stand Spec Role Limit Status
2× Beelink GTR9 Pro — AMD Strix Halo Ryzen AI Max+ 395, 128 GB LPDDR5X-8000 unified, Radeon 8060S (gfx1151), dual 10GbE — two commercially identical units Flagship qualification target: backend comparisons (Vulkan vs ROCm), unit-to-unit replication, multi-slot serving, RAG side-services Two units do not represent the whole production batch online
2× NVIDIA DGX Spark — GB10 GB10 Grace Blackwell, 20-core Arm, 128 GB unified, sm_121, ConnectX-7 — linked point-to-point over 200G RoCE aarch64/sm_121 portability, multi-node topologies, long-context and speculative decoding studies Expensive narrow testbed; results do not generalize to datacenter Blackwell online
RTX 5090 workstation Consumer Blackwell, 32 GB GDDR7, x86 host CUDA control lane, fine-tuning/distillation, consumer-GPU baselines One configuration; not an enterprise server online
Apple M1 Max, 64 GB Apple Silicon, 64 GB unified, macOS / MLX lane Apple/MLX smoke tests and small cross-platform anchors Not the current high-end Apple generation online

Commission a qualification

You buy a controlled process, not a positive result. Fees never depend on the verdict, funding is disclosed, and independent tests are separated from commissioned engineering.