CanItRun Logocanitrun.

Comparisons

59 GPU · 44 model · 11 app comparisons: VRAM, bandwidth, benchmarks, and compatibility, side by side.

Compare any two GPUs

Pick any two of the 86 GPUs we track (119 memory configurations, since some Apple Silicon chips ship in several RAM sizes) for a quick VRAM, bandwidth, and model-compatibility comparison.

SpecNVIDIA RTX 4090NVIDIA RTX 3090
VRAM24 GB24 GB
Bandwidth1008 GB/s936 GB/s
BackendCUDACUDA
TierConsumerConsumer
Models (native)53 / 9953 / 99
ModelNVIDIA RTX 4090NVIDIA RTX 3090
Llama 3.3 70B Instruct(70B)N/AN/A
Qwen 3.6 27B(27B)33.2 t/s(Q5_K_M)30.8 t/s(Q5_K_M)
Llama 3.1 8B Instruct(8B)38.4 t/s(BF16)35.6 t/s(BF16)
Qwen 2.5 7B Instruct(7.6B)41.8 t/s(BF16)38.8 t/s(BF16)

Estimated tokens/sec at 8k context, assuming the model fits natively in VRAM.

See the full NVIDIA RTX 4090 vs NVIDIA RTX 3090 comparison: analysis, FAQ, and every compatible model →