DiggTop ⌕

RTX 3080 vs RTX 5070

Pick a different pair →

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.

RTX 30809 sourced runs · best 277.8 tok/s
RTX 50705 verified runs · best 185.8 tok/s

Specs and evidence

RTX 3080RTX 5070
VRAM10 GB12 GB
Sourced runs on the board95
Models measured95
Best output tok/s277.8 tok/s185.8 tok/s
Highest measured peak VRAM9.7 GB9.0 GB
Street price (latest snapshot)——

Sourced rows only. Peak VRAM is recorded by the person who ran the benchmark, so it is a floor for what the card can hold, not a specification. Price snapshots.

Head-to-head

On the 2 models measured on both cards, RTX 3080 leads on 0, RTX 5070 on 2. The widest gap is on Ornith-1.5-9B: RTX 3080 82.8 tok/s vs RTX 5070 102.0 tok/s (RTX 5070 23% faster).

The measured matrix

ModelRTX 3080RTX 5070
LFM2.5-8B-A1B277.8 Q6_K—
NVIDIA-Nemotron-3-Nano-4B—185.8 Q4_K_M
Apodex-1.1-mini—182.3 IQ1_M
Ornith-1.5-9B82.8 Q6_K102.0 Q4_K_M
Qwen3.8-Flash-Next—81.8 Q2_0
Qwen3.8-27B-Uncensored74.1 IQ2_XXS—
Bonsai-27B72.9 Q1_0—
gemma-4-12B-it-qat71.2 Q4_0—
Ornith-1.5-35B-A3B64.4 Q4_K_M—
gpt-oss-20b57.1 MXFP4—
Qwen3.8-27B44.4 IQ2_XXS48.3 UD-Q2_K_XL
Muse-Glimmer-30B6.0 Q4_K_M—

Head-to-head (models tested on both): RTX 3080 0 · RTX 5070 2 · tied 0 · data as of Oct 30, 2026. Full rules: methodology.

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

↑