+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Hardware (https://www.datasculpting.ai/inference/forumdisplay.php?fid=4)
+--- Forum: GPUs (https://www.datasculpting.ai/inference/forumdisplay.php?fid=28)
+--- Thread: VRAM bottleneck on consumer cards for Llama (/showthread.php?tid=1355)
Pages:
1
2
Re: VRAM bottleneck on consumer cards for Llama - quiethouse - 10-19-2026
Appreciate the detail. I don't think your conclusion is far off. The biggest change for me was simplifying the stack instead of adding one more optimization layer.
Re: VRAM bottleneck on consumer cards for Llama - circuitwire58 - 10-19-2026
What exact setup are you running? Are you testing this on M3 Max or something else?
Re: VRAM bottleneck on consumer cards for Llama - thetarunner - 10-19-2026
Quote:Good point. The pattern around consumer GPUs has been pretty similar for me.
My first guess would be this: Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at tokens/sec. Not glamorous advice, but repeatable baselines save a lot of time.
If you post your exact settings, people here can probably narrow it down pretty fast.
Re: VRAM bottleneck on consumer cards for Llama - latentpeak22 - 10-19-2026
I don't think that's the whole story. I wouldn't optimize around that first. On my side the bigger swing came from the runtime and not the model.