{"paper":{"title":"A 35B Hybrid-Attention Mixture-of-Experts Model on a 6GB 2011 GPU: Hand-Written 4-bit CUDA Inference for Fermi","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cond-mat.other","authors_text":"A. C. Opus, J. Q. Lu","submitted_at":"2026-06-23T00:13:16Z","abstract_excerpt":"We report end-to-end inference of \\textbf{Qwen3.6-35B-A3B} -- a 35-billion-parameter, $\\sim$3B-active Mixture-of-Experts (MoE) model with a hybrid gated-delta-net / full-attention backbone -- on a \\textbf{2011 NVIDIA Tesla C2075} (Fermi, compute capability \\smtwenty, 6\\,GB), a GPU that predates tensor cores, native FP16 arithmetic, the \\texttt{DP4A} integer dot-product instruction, and support in every modern CUDA toolchain. Because the 4-bit model ($\\approx$10.5\\,GB) is roughly twice the device memory, we adopt a \\emph{hybrid} execution strategy: the GPU performs batched prompt \\emph{prefill}"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.24031","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.24031/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}