RTX 3080 vs RTX 4090

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 40902 verified runs · best 141.2 tok/s

Specs and evidence

	RTX 3080	RTX 4090
VRAM	10 GB	24 GB
Sourced runs on the board	9	2
Models measured	9	1
Best output tok/s	277.8 tok/s	141.2 tok/s
Highest measured peak VRAM	9.7 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

Only one model has been measured on both cards (Qwen3.8-27B). On that single data point RTX 3080 records 44.4 tok/s and RTX 4090 records 141.2 tok/s — treat it as one data point, not a ranking.

The measured matrix

Model	RTX 3080	RTX 4090
LFM2.5-8B-A1B	277.8 Q6_K	—
Qwen3.8-27B	44.4 IQ2_XXS	141.2 int4 (output head only)
Ornith-1.5-9B	82.8 Q6_K	—
Qwen3.8-27B-Uncensored	74.1 IQ2_XXS	—
Bonsai-27B	72.9 Q1_0	—
gemma-4-12B-it-qat	71.2 Q4_0	—
Ornith-1.5-35B-A3B	64.4 Q4_K_M	—
gpt-oss-20b	57.1 MXFP4	—
Muse-Glimmer-30B	6.0 Q4_K_M	—

Head-to-head (models tested on both): RTX 3080 0 · RTX 4090 1 · tied 0 · data as of Oct 30, 2026. Full rules: methodology.

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