+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Inference Engines (https://www.datasculpting.ai/inference/forumdisplay.php?fid=9)
+--- Forum: llama.cpp / GGUF (https://www.datasculpting.ai/inference/forumdisplay.php?fid=35)
+--- Thread: best GGUF for 24GB VRAM: early impressions (/showthread.php?tid=237)
Pages:
1
2
best GGUF for 24GB VRAM: early impressions - pixelcrate82 - 09-12-2026
Thought I'd post a small recipe because a lot of threads ask similar things.
This isn't revolutionary, but the combination of llama.cpp and 7900 XTX felt surprisingly usable once I tuned around prefill/decode split.
Maybe useful as a starting point for newer folks.
Re: best GGUF for 24GB VRAM: early impressions - northcraft90 - 09-12-2026
Thanks, that helps. I ended up in about the same place using llama.cpp. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.
Re: best GGUF for 24GB VRAM: early impressions - pixelcrate82 - 09-12-2026
Quote:Thanks, that helps. I ended up in about the same place using llama.cpp. I got better results once I stopped chasing one metric and just looked at whet
My first guess would be this: If you're on LM Studio, I'd confirm the version first and then reduce variables until the behavior is obvious. Once you know the plain path works, then add the faster path back in piece by piece.
Re: best GGUF for 24GB VRAM: early impressions - mellowwire98 - 09-12-2026
A couple things I'd check first. On M3 Max, the easiest win is often to back off the aggressive settings and see whether the problem survives.
Re: best GGUF for 24GB VRAM: early impressions - embershed99 - 09-12-2026
I'd approach it in a boring order. If you're on vLLM, I'd confirm the version first and then reduce variables until the behavior is obvious. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.
Re: best GGUF for 24GB VRAM: early impressions - llmpeak - 09-12-2026
Quote:I'd approach it in a boring order. If you're on vLLM, I'd confirm the version first and then reduce variables until the behavior is obvious. A lot of
A couple things I'd check first. If you're on llama.cpp, I'd confirm the version first and then reduce variables until the behavior is obvious.
Re: best GGUF for 24GB VRAM: early impressions - macroforge - 09-13-2026
subscribed, curious where this lands.
There are a few different conversations hiding inside this thread, so being explicit about the goal helps.
Re: best GGUF for 24GB VRAM: early impressions - visionyard23 - 09-13-2026
My first guess would be this: Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at tool calling. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.
Re: best GGUF for 24GB VRAM: early impressions - vectorport - 09-13-2026
Interesting, I hadn't tried that. The pattern around structured output has been pretty similar for me. The biggest change for me was simplifying the stack instead of adding one more optimization layer.
Re: best GGUF for 24GB VRAM: early impressions - tensorkite - 09-13-2026
subscribed, curious where this lands.