Can you help me improve my framerate?
Sure I can! First try not to run an LLM on your GPU while gaming. Hope that helped!
this post was submitted on 26 Mar 2025
45 points (80.8% liked)
Technology
67825 readers
5573 users here now
This is a most excellent place for technology news and articles.
Our Rules
- Follow the lemmy.world rules.
- Only tech related news or articles.
- Be excellent to each other!
- Mod approved content bots can post up to 10 articles per day.
- Threads asking for personal tech support may be deleted.
- Politics threads may be removed.
- No memes allowed as posts, OK to post as comments.
- Only approved bots from the list below, this includes using AI responses and summaries. To ask if your bot can be added please contact a mod.
- Check for duplicates before posting, duplicates may be removed
- Accounts 7 days and younger will have their posts automatically removed.
Approved Bots
founded 2 years ago
MODERATORS
It sounds like it only needs to consume resources (at least significant resources, I guess) when answering a query, which will already be happening when you're in a relatively "idle" situation in the game since you'll have to stop to provide the query anyway. It's also a Llama-based SLM (S = "small"), not an LLM for whatever that's worth:
Under the hood, G-Assist now uses a Llama-based Instruct model with 8 billion parameters, packing language understanding into a tiny fraction of the size of today’s large scale AI models. This allows G-Assist to run locally on GeForce RTX hardware. And with the rapid pace of SLM research, these compact models are becoming more capable and efficient every few months.
When G-Assist is prompted for help by pressing Alt+G — say, to optimize graphics settings or check GPU temperatures— your GeForce RTX GPU briefly allocates a portion of its horsepower to AI inference. If you’re simultaneously gaming or running another GPU-heavy application, a short dip in render rate or inference completion speed may occur during those few seconds. Once G-Assist finishes its task, the GPU returns to delivering full performance to the game or app. (emphasis added)
So they literally agree not using an LLM would increase your framerate. Also what would the machine know that the Internet couldn‘t answer as or more quickly while using fewer resources anyway? I‘m just saying this is an actually bad use case for AI precisely because it relies on the very hardware you‘re likely allocating to something else when you need it while there are better alternatives already. 8B models are fairly limited and still won‘t run very quickly or at all on slightly less beefy graphics cards than their horrendously expensive flagships of recent years while you‘re running a recent game. There just aren‘t all that many resources you can snatch from the process without crashing it.
So they literally agree not using an LLM would increase your framerate.
Well, yes, but the point is that at the time that you're using the tool you don't need your frame rate maxed out anyway (the alternative would probably be alt-tabbing, where again you wouldn't need your frame rate maxed out), so that downside seems kind of moot.
Also what would the machine know that the Internet couldn‘t answer as or more quickly while using fewer resources anyway?
If you include the user's time as a resource, it sounds like it could potentially do a pretty good job of explaining, surfacing, and modifying game and system settings, particularly to less technical users.
For how well it works in practice, we'll have to test it ourselves / wait for independent reviews.
Fuck no.
Fuck all these motherfuckers.
Lol. System requirements are 30, 40 & 50 series cards with 12GB of VRAM. Most of the cards do not have this due to Nvidia’s stinginess.
You can run your own LLM chatbot with https://ollama.com/
They have some really small ones that only require like 1GB of VRAM, but you’ll generally get better results if you pick the biggest model that fits on your GPU.
I've overclocked your GPU by 60mhz
What? Did you overclock core or memory? Would overclocking by 60mhz even make a difference in both cases? Did you adjust the voltage accordingly?
I don't know shit about overclocking and yet I still know that it's half-assing it
And DLSS Frame Gen is more of a last resort to get the most FPS out of your card (IMO); 92 FPS without it doesn't seem that low and frame gen probably wouldn't help much in that case anyway, unless you want it to hit VSYNC on a 120HZ monitor maybe? But it just turned off the framelimiter.... I'm confused
Probably gonna need a second GPU tho? One for the game, one or this thing.
the more you buy, the more you save, the brighter the jacket
Not if you're going to play Dwarf Fortress!
Is it missing ROPs too?
Ah yeah. Now I can just ask my GPU to get a team kill, all headshots, every match and feel like a winner. 😎
you're already a winner to me K@LANAKI