Run Qwen3-8B at ~18 tok/s on a Core Ultra laptop iGPU. Local-only LLM + VLM + ReAct agent stack with $0 token cost. Drop-in Claude Code backend.
-
Updated
Jun 8, 2026 - Python
Run Qwen3-8B at ~18 tok/s on a Core Ultra laptop iGPU. Local-only LLM + VLM + ReAct agent stack with $0 token cost. Drop-in Claude Code backend.
Pop!_OS fixes for ASUS ROG Zephyrus G16 (2025) — boot, sleep, NVIDIA, speakers, OEM kernel
Cross-platform local voice and vision assistant for Intel Core Ultra, using OpenVINO across CPU/GPU/NPU for LLM chat, Whisper STT, Silero VAD, TTS, and reactive camera presence detection.
Incident report: Proxmox VE kernel 6.17.13 IOMMU boot failure on Intel Arrow Lake (Core Ultra 9 285H)
CPU Frequency Manager for Hybrid Core Processors
Add a description, image, and links to the intel-core-ultra topic page so that developers can more easily learn about it.
To associate your repository with the intel-core-ultra topic, visit your repo's landing page and select "manage topics."