In-depth PC specs and hardware guidance for the AI era
AI Hardware Zukan

ミニPC・小型PC

GPUs & Graphics Cards

Why Oculink GPU Fails in Ollama: Dual Setup & Scheduling

Fix RTX 5060 Ti recognition in Ollama via Oculink. Step-by-step guide using CUDA_VISIBLE_DEVICES and OLLAMA_SCHED_SPREAD for RTX 5080 + RTX 5060 Ti dual-GPU setups.
2026.06.15 AI Hardware Zukan Editorial Team
GPUs & Graphics CardsLocal AIミニPC・小型PC
GPUs & Graphics Cards

RTX 4070 Super vs RTX 5060 Ti: VRAM Showdown for LLMs

Upgrading from RTX 4070 Super to RTX 5060 Ti boosts 14B model speed. See how the 4GB VRAM difference impacts performance across 15 models in our real-world test.
2026.06.15 AI Hardware Zukan Editorial Team
GPUs & Graphics CardsミニPC・小型PC
ComfyUI

ComfyUI Multi-GPU Guide: RTX 5080 + 4070 Super Real-World Tests

Real-world ComfyUI dual-GPU guide (RTX 5080 + 4070 Super): port separation for parallel jobs, why VRAM can't be pooled, and where Ollama is the exception.
2026.06.14 AI Hardware Zukan Editorial Team
ComfyUIGPUs & Graphics CardsミニPC・小型PC
Home
ミニPC・小型PC

Recent Posts

  • ComfyUI Upscale Eats 67GB RAM? Fix with External ESRGAN
  • Why Oculink GPU Fails in Ollama: Dual Setup & Scheduling
  • RTX 4070 Super vs RTX 5060 Ti: VRAM Showdown for LLMs
  • ComfyUI Multi-GPU Guide: RTX 5080 + 4070 Super Real-World Tests
  • RTX 5080 MoE Models: Power Drops to One-Quarter in Real-World Tests

Archives

  • June 2026
  • May 2026

Categories

  • AI Video Generation
  • ComfyUI
  • GPUs & Graphics Cards
  • Local AI
  • Local LLMs
  • PC構成
  • ミニPC・小型PC
AI Hardware Zukan
  • Privacy Policy
  • About
  • Contact
© 2026 AI Hardware Zukan.
  • Home
  • Top