AMD GPU for Local LLMs: ROCm vs Vulkan, and Can the RX 7900 XTX or 9070 XT Do the Job?
Using an AMD GPU for local LLMs? See Ollama’s support list, choose ROCm or Vulkan, compare RX 7900 XTX and 9070 XT bandwidth, and fix common errors.
-
-
Laptop for Local LLMs: How to Choose VRAM, Bandwidth, Cooling and Mac Options (2026)
Choosing a laptop for local LLMs? Compare RTX 50 laptop VRAM, bandwidth and power limits, cooling, and Mac unified memory, and see what 8GB to 24GB can run.
-
Best GPU for Local LLMs: A VRAM Tier Table (2026)
Find the best GPU for local LLM use: VRAM tiers from 8GB to 32GB, matching models, bandwidth, power draw and dated price ranges, plus buying pitfalls.
-
How to Run an LLM Locally: Hardware You Need and How to Pick a Model (2026)
Want to run an LLM locally? Learn how much VRAM you need, which models fit 8GB to 48GB, and how to get your first model running with Ollama in five steps.
-
Local LLM PC Build: Four Tiers From 12GB to 32GB VRAM
Planning a local LLM PC build? Four VRAM tiers from 12GB to 32GB, with CPU, RAM, PSU and storage advice, a GPU price snapshot and a build checklist.
-
Ollama Not Using GPU? How to Fix It on NVIDIA, AMD, Mac and Docker
Ollama not using GPU? Confirm with ollama ps, then check NVIDIA drivers, AMD ROCm, Vulkan, Mac and Docker, with the env vars and log paths to use.
-
Running an LLM on 24GB VRAM: What Can an RTX 3090 / 4090 Run?
Which LLMs fit on 24GB VRAM? 27B–32B dense and 30B MoE models with memory estimates, long-context headroom, 3090 vs 4090, and why 70B doesn’t fit.
-
Run an LLM on 8GB VRAM: What Can an 8GB GPU Run? Model Picks
Run an LLM on 8GB VRAM: Ollama picks for chat, reasoning, coding and vision with file sizes, context settings, 8GB card comparison and upgrade advice.
