From 8f59ea9433d9009b973a1b8a33831ddced3a159d Mon Sep 17 00:00:00 2001 From: comfyanonymous <121283862+comfyanonymous@users.noreply.github.com> Date: Fri, 8 Nov 2024 15:24:56 -0500 Subject: [PATCH] Updated Which GPU should I buy for ComfyUI (markdown) --- Which-GPU-should-I-buy-for-ComfyUI.md | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) diff --git a/Which-GPU-should-I-buy-for-ComfyUI.md b/Which-GPU-should-I-buy-for-ComfyUI.md index 36baf91..45cfdd2 100644 --- a/Which-GPU-should-I-buy-for-ComfyUI.md +++ b/Which-GPU-should-I-buy-for-ComfyUI.md @@ -12,6 +12,28 @@ All Nvidia GPUs from the last 10 years (since Maxwell/GTX 900) are supported in 3000 series and above are recommended for best performance. More VRAM is always preferable. +
+Why you should avoid older generations if you can. + +
+ +Older generations of cards will work however performance might be worse than expected because they don't support certain operations. + +Here is a quick summary of what is supported on each generation: + +* 40 series (ada): fp16, bf16, fp8 +* 30 series (ampere): fp16, bf16 +* 20 series (turing): fp16 +* 10 series (pascal) and below: only slow full precision fp32. + +Models are inferenced in fp16 or bf16 for best quality depending on the model with the option for fp8 on some models for less memory/more speed at lower quality. + +Note that this table doesn't mean that it's completely unsupported to use fp16 on 10 series for example it just means it's going to be slower because the GPU can't handle it natively. + +Don't be tempted by the cheap pascal workstation cards with lots of vram, your performance will be bad. + +
+ # B Tier ## AMD (Linux)