Local AI Hardware
GPUs, mini PCs, and unified-memory boxes for running local LLMs, with tested tokens/sec.
-
1
Part 1 of 7
Best GPU for LLMs in 2026: Tested by VRAM, Budget, and Model Size
The right graphics card for running large language models locally comes down to one number more than any other: how much VRAM it carries. That single…
17 min read·Jun 2026
-
2
Part 2 of 7
How Much VRAM Do You Need to Run an LLM (7B to 70B)
A 70B model needs about 42 GB of VRAM at Q4_K_M. A 32B fits in 24 GB. A 13B needs about 11 GB, and a 7B…
14 min read·Jun 2026
-
3
Part 3 of 7
Unified Memory vs VRAM for AI, Explained
When you go shopping for hardware to run AI models locally, you run into two completely different ways of attaching memory to a processor, and the…
13 min read·Jun 2026
-
4
Part 4 of 7
Best Mini PC for Local AI and Running LLMs
A 128 GB mini PC now holds a 70B model that a 24 GB graphics card cannot. It will not run that dense 70B fast: expect…
12 min read·Jun 2026
-
5
Part 5 of 7
Mac Mini vs Mini PC vs GPU for Local LLMs
Three ways to run a 70B model at home, and each one wins at something different. A Mac holds a big model and runs it at…
12 min read·Jun 2026
-
6
Part 6 of 7
Used RTX 3090 vs RTX 5090 for Local AI: Is the Cheaper Card Still King?
A tested head-to-head of the used RTX 3090 and the new RTX 5090 for running local LLMs, with real tokens per second, the price gap, and…
8 min read·Jun 2026
-
7
Part 7 of 7
AMD Ryzen AI Max+ 395 Mini PCs Compared: Framework Desktop vs GMKtec EVO-X2 vs Beelink GTR9 Pro
All three of these mini PCs run the same silicon: the AMD Ryzen AI Max+ 395 “Strix Halo”, 16 Zen5 cores, the Radeon 8060S iGPU, and…
11 min read·Jun 2026