Bartowski
Publishes GGUF quantizations of open models and contributes to llama.cpp; ML engineer at Red Hat
- Senior Machine Learning Engineer, Red Hat1
- Co-owner of the tiled CPU code (ggml/src/ggml-cpu/tiled), llama.cpp project3
Bartowski is a public handle; the Hugging Face profile under that name gives Bartowski's role as Senior Machine Learning Engineer at Red Hat. The profile hosts GGUF quantizations of open language models for llama.cpp and compatible runtimes; model cards such as the one for Qwen3.8-27B name the llama.cpp release used for quantization and note imatrix calibration. In llama.cpp itself, CODEOWNERS lists Bartowski as a co-owner of the tiled CPU code, and Bartowski's commits cover IQ quantization fixes and speedups, imatrix tooling, and support for new model architectures.1234
Work
llama.cppOpen-source code
CODEOWNERS lists bartowski1182 with one other contributor for ggml/src/ggml-cpu/tiled. Commits authored from September 2025 to September 2026 include IQ-quant correctness fixes and AVX2 prompt-processing speedups, a shared imatrix loader, per-slot context for llama-server, and support for architectures such as GLM 4.6 and AfmoeForCausalLM. The repository is MIT-licensed.345
GGUF quantizations on Hugging Face (external site: huggingface.co)Open weights
Publishes quantized GGUF versions of open models under the bartowski account. The model card for Qwen3.8-27B-GGUF, for example, says the quants were made with llama.cpp release b10896 using imatrix calibration, and gives the repository's license as Apache-2.0.12
This profile covers public professional work only, from the sources below. It is not an endorsement or a ranking. To correct or remove it, use the correction form.