RTX 3090 x4 vs RTX 5070

GPU AGPU B

Best sourced output tok/s per model (single-stream generation) — engine and version, quantization, context and a source link on every row. Hover a value for the quant.

Sourced data on this pair is thin — most of the board is still partial. Submit your own run and help fill the matrix: one prompt, three steps, no downloads.

RTX 3090 x41 sourced run · best 145.8 tok/s

RTX 50705 verified runs · best 185.8 tok/s

Model	RTX 3090 x4	RTX 5070
NVIDIA-Nemotron-3-Nano-4B	—	185.8 Q4_K_M
Apodex-1.1-mini	—	182.3 IQ1_M
Qwen3.8-Flash-Next	145.8 W4A16+FP8-KV	81.8 Q2_0
Ornith-1.5-9B	—	102.0 Q4_K_M
Qwen3.8-27B	—	48.3 UD-Q2_K_XL

Head-to-head (models tested on both): RTX 3090 x4 1 · RTX 5070 0 · tied 0 · data as of Oct 6, 2026. Full rules: methodology.

Related reading: RTX 5090 vs 3090 · quantization · Value index · Full board