Gemma 4 26B-A4B inference in ~2 GB of RAM on any M-series MacBook
Free-first, model-adaptive coding agent runtime that makes local small LLMs work reliably with harness, checkpointing, verification, cache-aware context, and free-model fallback.
Docker Compose stack for serving a local, OpenAI-compatible LLM (vLLM on Intel XPU) on an Intel Arc Pro B60 GPU — reproducible config with operator and developer docs.
Zero-training brand exposure auditor — detect any logo in any broadcast using Gemma 4 vision on Apple Silicon
Configuration layer and prompt engineering toolkit for Gemma 4 26B-A4B. Optimized for Google AI Studio.
chatdsl for repo evaluation - uses chatybot. ( pip install chatybot )
To associate your repository with the gemma4-26b-a4b topic, visit your repo's landing page and select "manage topics."