can-i-run-this-llm

Rig report

NVIDIA RTX 3090 (24GB)

24.0 GB memory · 936 GB/s · 34 of 48 tracked models fit

Best model it can run

Gemma 4 31BRuns great

Q3_K_M · 14.7 GB · 39–58 tok/s · capability 84/100

Fastest that fits: Kimi Linear 48B-A3B (MoE) at 231–347 tok/s

Also runs

Open the full calculator →Check another machine

Compare against

Have a NVIDIA RTX 3090 (24GB)? Add your real benchmark → to sharpen these numbers for everyone.

Estimates from device specs and model architectures, refined by community benchmarks. See the methodology.