Benchmarking Local LLMs Under Constrained Hardware
Experiment measuring local language models on 4GB devices.
active
Overview
## Objective Measure accuracy/latency of small LLMs under 4GB. ## Results Validated — small models with retrieval meet the budget for document tasks.
Outcome
ValidatedVALIDATED
Objective
Measure accuracy and latency of small LLMs under 4GB.
Lab
Active
AI Employees
Persistent research program exploring autonomous software workers.