@inproceedings{21932,
  abstract     = {We present LLMQ, an end-to-end CUDA/C++ implementation for medium-sized language-model training, e.g. 3B to 32B parameters, on affordable, commodity GPUs. These devices are characterized by low memory availability and slow communication compared to datacentre-grade GPUs. Consequently, we showcase a range of optimizations that target these bottlenecks, including activation checkpointing, offloading, and copy-engine based collectives. LLMQ is able to train or fine-tune a 7B model on a single 16GB mid-range gaming card, or a 32B model on a workstation equipped with 4 RTX 4090s. This is achieved while executing a standard 8-bit training pipeline, without additional algorithmic approximations, and maintaining FLOP utilization of around 50%. The efficiency of LLMQ rivals that of production-scale systems on much more expensive cloud-grade GPUs.},
  author       = {Schultheis, Erik and Alistarh, Dan-Adrian},
  booktitle    = {2nd Conference on Parsimony and Learning},
  issn         = {2640-3498},
  location     = {Stanford, CA, United States},
  pages        = {265--284},
  publisher    = {ML Research Press},
  title        = {{LLMQ: Efficient lower-precision LLM training for consumer GPUs}},
  volume       = {328},
  year         = {2026},
}