RTX 3070

NVIDIA · 8 GB · 448 GB/s

4 models4 model configurations4 exact recipes

Representative image: 3070/3070 Ti family og:image depicts the 3070 Ti Founders Edition; representative for the 3070 (same FE chassis). — 3070/3070 Ti family og:image depicts the 3070 Ti Founders Edition; representative for the 3070 (same 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

4 configurations · 4 recipes

Gemma 4 12B

RTX 30708 GB1 card per machine · 1 machine

TabbyAPIEXL3 3 bpw

36.5decode tok/s

677prefill tok/s

32Kcontext

Tested on this card · Sep 26, 2026

Full recipe ›

LFM2.5-2.6B

RTX 30708 GB1 card per machine · 1 machine

SGLangFormat not recorded

67.2decode tok/s

—prefill tok/s

128Kcontext

Earlier check · Sep 3, 2026

Full recipe ›

Qwen3.6-35B-A3B

RTX 30708 GB1 card per machine · 1 machine

Host RAM: ≥ 24 GB free
Disk: ≥ 25 GB NVMe

SGLangEXL3 3 bpw

45.9decode tok/s

1,756prefill tok/s

128Kcontext

Tested on this card · Oct 15, 2026

Full recipe ›

Qwen3.8-Flash-Next

RTX 30708 GB1 card per machine · 1 machine

Host RAM: ≥ 48 GB free
Disk: ≥ 64 GB NVMe

SGLangEXL3 2.05 bpw

34.9decode tok/s

925prefill tok/s

64Kcontext

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	8 GB GDDR6
Bandwidth	448 GB/s
Architecture	NVIDIA Ampere
CUDA cores	5,888
Tensor cores	3rd generation
RT cores	2nd generation

Precision	Dense TFLOPS	2:4 sparse
INT8	162.6	325.2
FP16	81.3	162.6
BF16	40.6	81.3
TF32	20.3	40.6
FP32	20.3	–

MSRP

$499

Listing	Price	Seen	Where
MSRP	$499	2020-10	NVIDIA ›

Sources: NVIDIA, NVIDIA (2), NVIDIA (3)