Run local LLMs on Apple Silicon via [mlx-lm](https://github.com/ml-explore/mlx-examples/tree/main/llms/mlx_lm). Menubar app + CLI with an OpenAI-compatible API on `localhost:11434`.
-
Updated
May 20, 2026 - Swift
#
ollama-compatible
Here are 4 public repositories matching this topic...
Lightweight evaluation framework for Retrieval Augmented Generation systems, focused on simplicity and long-term consistency.
evaluation-framework vector-embeddings retrieval-augmented-generation llm-evaluation openai-compatible ollama-compatible
-
Updated
Apr 29, 2026 - Python
CLI + API server to download, manage, and run 500K+ HuggingFace models locally with Ollama & OpenAI compatibility
privacy ai transformers inference self-hosted mlx model-serving huggingface openai-api llm llama-cpp vllm local-llm gguf ollama-compatible
-
Updated
May 25, 2026 - Python
Android AI inference server with OpenAI-compatible API. Turn your phone into a local LLM co-processor — runs MLC LLM (GGUF) + LiteRT-LM (.litertlm) with dual-engine routing, bearer auth, thermal governor, KV cache, and resumable model downloads. No cloud, no GPU, no friction.
android kotlin machine-learning ai inference llama ktor litert foreground-service npu on-device-ai openai-api play-asset-delivery llm local-ai gguf mlc-llm ollama-compatible
-
Updated
May 24, 2026 - Kotlin
Improve this page
Add a description, image, and links to the ollama-compatible topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the ollama-compatible topic, visit your repo's landing page and select "manage topics."