Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Make use of Intel Arc Series GPU to Run Ollama, StableDiffusion, Whisper and Open WebUI, for image generation, speech recognition and interaction with Large Language Models (LLM).
| Date | Stars |
|---|---|
| 2026-08-05 | 394 |
| 2026-08-07 | 395 |
| 2026-08-09 | 396 |
| 2026-08-10 | 397 |
| 2026-08-11 | 398 |
| 2026-08-17 | 399 |
| 2026-08-19 | 399 |
| 2026-08-21 | 400 |
| 2026-08-22 | 401 |
| 2026-08-23 | 401 |
| 2026-08-28 | 403 |
| 2026-08-30 | 404 |
| 2026-09-01 | 406 |
| 2026-09-04 | 407 |
| 2026-09-05 | 409 |
| 2026-09-07 | 410 |
| 2026-09-08 | 412 |
| 2026-09-09 | 412 |
| 2026-09-10 | 413 |
| 2026-09-11 | 412 |
| 2026-09-16 | 413 |
| 2026-09-19 | 414 |
| 2026-09-22 | 415 |
| 2026-09-24 | 416 |
| 2026-09-25 | 418 |
| 2026-09-26 | 419 |
| 2026-09-28 | 418 |
| 2026-09-30 | 418 |
| 2026-10-02 | 418 |
| 2026-10-03 | 419 |
| 2026-10-07 | 420 |
| 2026-10-08 | 421 |
| 2026-10-12 | 422 |
| 2026-10-15 | 423 |
| 2026-10-16 | 424 |
| 2026-10-17 | 425 |
| 2026-10-24 | 426 |
| 2026-10-29 | 427 |
| 2026-10-30 | 428 |
| 2026-10-31 | 429 |
| 2026-11-01 | 430 |
| 2026-11-04 | 430 |
Today
— stars today
This week
+4 stars this week
This month
+11 stars this month
Momentum
19.0
growth rate 0.94%/day
# Run Ollama, Stable Diffusion and Automatic Speech Recognition with your Intel Arc GPU [[Blog](https://blog.eleiton.dev/posts/llm-and-genai-in-docker/)] Effortlessly deploy a Docker-based solution that uses [Open WebUI](https://github.com/open-webui/open-webui) as your user-friendly AI Interface and [Ollama](https://github.com/ollama/ollama) for integrating Large Language Models (LLM). Additionally, you can run [ComfyUI](https://github.com/comfyanonymous/ComfyUI) or [SD.Next](https://github.com/vladmandic/sdnext) docker containers to streamline Stable Diffusion capabilities. You can also run an optional docker container with [OpenAI Whisper](https://github.com/openai/whisper) to perform Automatic Speech Recognition (ASR) tasks. The Ollama container runs a **native [SYCL](https://github.com/ggml-org/llama.cpp/blob/master/docs/backend/SYCL.md) (or [Vulkan](https://github.com/ggml-org/llama.cpp/blob/master/docs/build.md#vulkan)) llama.cpp backend** built directly from upstream Ollama — no IPEX-LLM. The Stable Diffusion and Whisper containers are still optimized for Intel Arc GPUs using [Intel® Extension for PyTorch](https://github.com/intel/intel-extension-for-pytorch).  ## Services 1. Ollama * Runs Ollama with a **native llama.cpp `ggml-sycl` backend**, compiled from Ollama source against Intel® oneAPI (`icpx` / Level Zero). No IPEX-LLM dependency. * The image is built locally in two stages (see [`ollama-sycl/Dockerfile`](ollama-sycl/Dockerfile)): stage 1 builds `libggml-sycl.so` with oneAPI; stage 2 drops it next to the official Ollama binary on a slim Ubuntu runtime with the Intel GPU user-space drivers (Level Zero, compute-runtime, IGC, GMM). * A **Vulkan** alternative is also provided ([`docker-compose.ollama-vulkan.yml`](docker-compose.ollama-vulkan.yml)) using the stock `ollama/ollama` image. On Meteor Lake / Xe-LPG iGPUs the Vulkan backend is often competitive with SYCL while requiring no custom build — worth benchmarking on your hardware. * Runtime behavior is tuned via a `.env` file (see [`.env.example`](.env.example)) — context length, KV-cache type, flash attention, GPU offload, etc. * Exposes port `11434` for connecting other tools to your Ollama service. 2. Open WebUI * Uses the official distribution of Open WebUI. * `WEBUI_AUTH` is turned off for authentication-free usage. * `ENABLE_OPENAI_API` and `ENABLE_OLLAMA_API` flags are set to off and on, respectively, allowing interactions via Ollama only. * `ENABLE_IMAGE_GENERATION` is set to true, allowing you to generate images from the UI. * `IMAGE_GENERATION_ENGINE` is set to automatic1111 (SD.Next is compatible). 3. ComfyUI * The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. * Uses as the base container the official [Intel® Extension for PyTorch](https://pytorch-extension.intel.com/installation?platform=gpu) 4. SD.Next * All-in-one for AI generative image based on Automatic1111 * Uses as the base container the official [Intel® Extension for PyTorch](https://pytorch-extension.intel.com/installation?platform=gpu) * Uses a customized version of the SD.Next [docker file](https://github.com/vladmandic/sdnext/blob/dev/configs/Dockerfile.ipex), making it compatible with the Intel Extension for Pytorch image. 5. OpenAI Whisper * Robust Speech Recognition via Large-Scale Weak Supervision * Uses as the base container the official [Intel® Extension for PyTorch](https://pytorch-extension.intel.com/installation?platform=gpu) ## Setup First, create your `.env` file from the example and adjust it to your hardware if needed: ```bash $ git clone https://github.com/eleiton/ollama-intel-arc.git $ cd ollama-intel-arc $ cp .env.example .env ``` Then start Ollama + Open WebUI with the **native SYCL** backend (this builds the Ollama image locally the first time): ```bash $ podman compose -f docker-compose.ollama-sycl.yml up -d --bui
Excerpt of 12,713 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:e02ec461838d269b, topic:stable-diffusion, desc:image generation, readme:image generation