From b794b103e868f4464363316b8373ee05aa4962b8 Mon Sep 17 00:00:00 2001 From: Md Tasnimul Hoque Date: Fri, 9 Oct 2026 23:40:26 +0530 Subject: [PATCH] Simplify memory requirements section in FAQ Removed redundant lines about model memory requirements. --- admin/docs/faq.md | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/admin/docs/faq.md b/admin/docs/faq.md index f94fc842..f3807d72 100644 --- a/admin/docs/faq.md +++ b/admin/docs/faq.md @@ -38,9 +38,7 @@ defensive one. **The AI is the variable, and it is the model rather than NOMAD.** Ollama idles at roughly 1.2GB, and a model needs about its download size resident while it answers, -so an 8B model at ~4.6GB wants about that much on top. **8GB is workable for a small -model, 16GB is comfortable, and 32GB is the recommendation if you want to run larger -ones.** +so an 8B model at ~4.6GB wants about that much on top. **8GB is workable for a small model, 16GB is comfortable, and 32GB is the recommendation if you want to run larger ones.** Where that memory comes from depends on your hardware. With a discrete GPU the model loads into VRAM and never touches system RAM, so VRAM is the number that limits which