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 306013 sourced runs · best 310.4 tok/s
RTX 40700 verified runs · best — tok/s
Specs and evidence
RTX 3060
RTX 4070
VRAM
12 GB
12 GB
Sourced runs on the board
13
0
Models measured
12
0
Best output tok/s
310.4 tok/s
—
Highest measured peak VRAM
9.3 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.
12 rows · 12 models on RTX 3060, 0 on RTX 4070 — no verified overlap yet, each side shows its own bests · data as of Oct 17, 2026. Full rules: methodology.