Robinson Labs

AI & ML interests

I run a self funded solo AI research lab. I have 15+ years experience in developing and designing scalable solutions on the ServiceNow platform. By day I work on enterprise platforms. By night I run a local-first AI operating system on hardware I own, and I forge open models to run on it. The cluster. It started as a pile of PCs under the desk and a mining-era stack of GPUs. Today it is thirteen machines on a 10-gigabit fabric, two NAS boxes, a custom water loop, and a llama.cpp cluster with over two million tokens of live context across three brain nodes. It serves 14b, 35b, 88b, and 122b text models, a 30b vision model, an embedding and reranking fleet, and an SDXL image generation box that does four images per pass. The models here are not drive-by uploads. They are built, quantized, and run daily on that cluster. What we publish: Abliterated models: single-direction weight orthogonalization that relaxes the hard-refusal reflex while keeping harm guardrails intact by design. Abliterated REAP builds: we abliterate community REAP expert-pruned MoE variants (Qwen3.5-122B and its REAP-30 / REAP-20 cuts) and publish the pair, bf16 base plus the quant ladder. imatrix GGUF quant ladders: importance-matrix-weighted, Q6_K down to IQ2, so you pick your size and quality tradeoff. Custom cluster-fit quants: recipes tuned to a specific VRAM and context budget, attention-path precision kept high where it counts and the experts run lighter. The ethos. Every release ships with full provenance and credits the upstream base author. Own your models, your memory, your tools. Lean, efficient, no bloat, runs on anything. The same rule that runs the cluster.

Recent Activity

stevorob  updated a model 1 day ago

RobinsonLabs/requests

stevorob  published a model 1 day ago

RobinsonLabs/requests

stevorob  updated a model 1 day ago

RobinsonLabs/Qwen3.6-35B-A3B-abliterated

View all activity

Team members 1