RTX 3080

NVIDIA · 12 GB

1 models1 model configurations1 exact recipes

Representative image: 3080/3080 Ti family og:image shows the 3080 Ti FE; representative for the 3080 (identical FE chassis). — 3080/3080 Ti family og:image shows the 3080 Ti FE; representative for the 3080 (identical FE chassis). NVIDIA ›

Model configurations

Each card is a model and hardware setup, including any documented host RAM, storage or CPU requirements. Select a recipe to update its speeds, context and exact command.

Search configurations

Sort by

1 configurations · 1 recipes

Bonsai 2 9B

RTX 308012 GB1 card per machine · 1 machine

llama.cppFormat not recorded

155decode tok/s

2,654prefill tok/s

32Kcontext

Tested on this card · Oct 16, 2026

Full recipe ›

Speeds are the selected recipe’s recorded measurements, not estimates; “—” means unmeasured. Evidence distinguishes checks on this card, sibling-card checks, earlier checks and publisher reports.

Hardware

Memory	12 GB GDDR6X
Bandwidth	912 GB/s
Architecture	NVIDIA Ampere
CUDA cores	8,960
Tensor cores	3rd generation
RT cores	2nd generation

Precision	Dense TFLOPS	2:4 sparse
INT8	238	476
FP16	119	238
BF16	59.5	119
TF32	29.8	59.5
FP32	29.8	–

Sources: NVIDIA