Home
Start here
Local AI
Fixes & guides
Builds & gear
Popular AI podcast
About
Home
Start here
Local AI
Fixes & guides
Builds & gear
Popular AI podcast
About
Subscribe
Sign in
Latest
Top
Discussions
Science proves AI users are dumb
A viral AI literacy study is being used to mock AI fans as tech illiterates. But what the study really demonstrates is far stranger.
Jun 22
•
Ben Geudens
2
1
1
The RTX 5090 for local AI: fast bandwidth, same VRAM wall
For local AI, the RTX 5090 shines with 8B to 32B models. Bigger 70B workloads still point to RTX PRO 6000, H100, or cloud GPUs.
Jun 19
•
Popular AI
1
1
1
Are dual RTX 3090s still worth buying for local AI in 2026?
Thinking about swapping an RTX 4080 for dual RTX 3090s? Here is when 48GB VRAM matters for local AI, and when it is not worth it.
Jun 15
•
Popular AI
2
1
1
4x or 8x RTX 3090 local AI servers: still worth building in 2026?
A practical guide to 4x and 8x RTX 3090 local AI servers, covering VRAM, EPYC, Threadripper Pro, power, cooling, NVLink, and value.
Jun 14
•
Popular AI
4
1
1
Why Claude AI wants this man in prison
Claude AI reversed two Dutch legal phrases in a high-stakes translation. Here is what went wrong and how to verify AI legal output.
Jun 13
•
Popular AI
2
1
1
Should you buy the RTX 5060 Ti 16GB or RX 9070 XT for local AI?
Choosing a GPU for local LLMs? Here’s when to buy the RTX 5060 Ti 16GB, when the RX 9070 XT makes sense, and what to avoid.
Jun 9
•
Popular AI
1
1
1
ComfyUI extra_model_paths.yaml not working? Here’s the fix
ComfyUI not finding checkpoints, LoRAs, VAEs, or upscalers? Here’s how to repair extra_model_paths.yaml and confirm it works.
Jun 8
•
Popular AI
1
1
1
How to fix Ollama CPU offloading and slow inference
Ollama suddenly slow? Learn how to diagnose CPU offloading, KV cache bloat, context size, and GPU layer splits.
Jun 7
•
Popular AI
1
1
1
How to fix ComfyUI Desktop “unrecognized arguments: --normalvram” crashes
ComfyUI Desktop crashing with “unrecognized arguments: --normalvram”? Learn how to remove bad launch flags, update safely, check logs, and run ComfyUI…
Jun 6
•
Popular AI
1
1
1
How to run Gemma 4 31B locally with Ollama for private writing
Gemma 4 31B can handle long-context writing locally, but memory matters. Here is how to set it up without chasing 256K too soon.
Jun 5
•
Popular AI
3
1
1
llama.cpp vs Ollama vs LM Studio: which is fastest in 2026?
A practical 2026 guide to llama.cpp vs Ollama vs LM Studio, covering benchmarks, GPU offload, context length, APIs and local AI privacy.
Jun 4
•
Popular AI
2
1
1
The ChatGPT sidebar sucks now. Here’s how to fix it.
If your ChatGPT pinned chats, GPTs, or Projects disappeared, do not panic. Here is what changed and how to get them back.
Jun 3
•
Ben Geudens
1
1
1
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts
