AI & ML interests

Independent applied AI research. Large language models, Mixture-of-Experts (MoE), local AI, bounded-memory execution, GPU inference, AMD Ryzen AI / ROCm, model integrity, high-assurance on-premises AI, and autonomous engineering systems.

Recent Activity

Hutch66  updated a Space about 3 hours ago
nh-applied/QES
Hutch66  updated a Space about 3 hours ago
nh-applied/README
Hutch66  published a Space about 10 hours ago
nh-applied/QES
View all activity

Organization Card

NH Applied

Independent applied AI research focused on local large-model execution, Mixture-of-Experts inference, model integrity, high-assurance on-premises AI, and autonomous engineering systems.

Current research — QES

Running a 1-trillion-parameter, ~375 GB Kimi K2.5 model on one 128 GB AMD Ryzen AI MAX+ 395 Windows PC.

QES investigates whether very large Mixture-of-Experts models can remain locally executable when their routed-expert capacity substantially exceeds available system memory.

The work has demonstrated cross-family execution across:

  • Qwen3-235B
  • Kimi K2.5

For Kimi K2.5, the published sustained validation reached 0.432091702 tokens/s over 128 generated tokens, with all 129 output token IDs exactly matching the frozen historical reference, 61,440 GPU expert executions, 7,680 authoritative correctness checks, and zero GPU errors.

QES also incorporates model-integrity measures including pre-execution verification, protected expert stores, continuous correctness checking, and fail-closed qualification behaviour.

QES technical white paper v2.7

DOI: https://doi.org/10.5281/zenodo.22730031

GitHub

https://github.com/nigelhutch/nh-applied-qes

Contact

Technical discussion, research collaboration or commercial enquiries:

NH Applied — nhapplied@gmail.com


Nigel Hutchinson / NH Applied

models 0

None public yet

datasets 0

None public yet