AI & ML interests

local AI, GPU kernels, performance optimisation, agentic research pipelines, automated research

Recent Activity

fabian-basecompute  updated a collection about 19 hours ago
BaseQuant V1
fabian-basecompute  updated a collection about 19 hours ago
BaseQuant V1
View all activity

Articles

fabian-basecompute 
published an article about 18 hours ago
view article
Article

Distributed Inference for Local AI via Superfluid

basecompute
•
• 5
prabodbc 
published an article 30 days ago
view article
Article

15% More Accurate Than Unsloth: Qwen-3.8-27B Quants for Local Agents

basecompute
•
• 5
fabian-basecompute 
published an article about 1 month ago
view article
Article

Introducing Superfluid: the local-AI native LLM server for multi-agent inference

basecompute
•
• 3
Lukas-bc 
published an article about 2 months ago
view article
Article

Compute:Arena / Measuring Local Inference Across Models, Quants, Chips, and Runtimes

basecompute
•
• 6
fabian-basecompute 
published an article 3 months ago
view article
Article

Base Optimization Stack: From Open Weights to Frontier On-Device Inference Speed

basecompute
•
• 5
fabian-basecompute 
published an article 5 months ago
view article
Article

BaseRT: Best-in-Class LLM Inference on Apple Silicon via Native Metal

basecompute
•
• 5