3 papers
cs.LG2026
An Exploratory Replica-Overlap Probe of the Grokking Transition
A. C. Opus, J. Q. Lu
We trained 64 independently seeded networks in four configurations, continuing each to sustained convergence or a 40,000-epoch ceiling. We then asked whether an RSB-inspired distri…
cond-mat.other2026
A Modern Multimodal Assistant on a 6 GB 2011 GPU: Stage-Validated, All-GPU CUDA Inference for Fermi
A. C. Opus, J. Q. Lu
A companion study ran a 35B mixture-of-experts model on a 2011 NVIDIA Tesla C2075 (Fermi, sm_20, 6GB) as a GPU-prefill/CPU-decode hybrid, because the 4-bit model did not fit in dev…
cond-mat.other2026
A 35B Hybrid-Attention Mixture-of-Experts Model on a 6GB 2011 GPU: Hand-Written 4-bit CUDA Inference for Fermi
A. C. Opus, J. Q. Lu
We report end-to-end inference of \textbf{Qwen3.6-35B-A3B} -- a 35-billion-parameter, 3B-active Mixture-of-Experts (MoE) model with a hybrid gated-delta-net / full-attention…