OpenAI API server for OpenVino - when OVMS is too big
-
Updated
Jun 1, 2026 - Python
#
arc-b60
Here are 3 public repositories matching this topic...
Run any LLM locally on Intel Arc GPUs. Gemma, Qwen, vision and audio models optimized for budget hardware. · Dirty South Alpha™
gpu vulkan homelab gemma on-device-ai oneapi llm local-inference intel-arc llama-cpp local-llm llm-inference ollama qwen ipex-llm self-hosted-ai battlemage arc-b60
-
Updated
Sep 18, 2026 - JavaScript
Real-world LLM inference benchmarks on Intel Arc (Battlemage B60) — measured tok/s, quantization recipes, and MoE-vs-dense data, not synthetic claims. · Dirty South Alpha™
vulkan benchmarks moe quantization intel-arc llama-cpp gpu-inference local-llm llm-inference qwen self-hosted-ai battlemage arc-b60
-
Updated
Sep 18, 2026 - Shell
Add this topic to your repo
To associate your repository with the arc-b60 topic, visit your repo's landing page and select "manage topics."