RTX 5070 Ti Laptop

NVIDIA · 12 GB

3 models3 model configurations3 exact recipes

Representative image: Laptop GPU with no standalone card; NVIDIA GeForce RTX 50-series laptops marketing image used as representative. — Laptop GPU with no standalone card; NVIDIA GeForce RTX 50-series laptops marketing image used as representative. 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

3 configurations · 3 recipes

Gemma 4 12B

RTX 5070 Ti Laptop12 GB1 card per machine · 1 machine

TabbyAPIEXL3 4 bpw

58.7decode tok/s

1,452prefill tok/s

64Kcontext

Tested on a sibling · Sep 27, 2026

Full recipe ›

Qwen3.5-9B

RTX 5070 Ti Laptop12 GB1 card per machine · 1 machine

TabbyAPIEXL3 4 bpw

68.7decode tok/s

—prefill tok/s

128Kcontext

Earlier check · Sep 25, 2026

Full recipe ›

Qwen3.8-27B

RTX 5070 Ti Laptop12 GB1 card per machine · 1 machine

TabbyAPIEXL3 2.2 bpw

59.1decode tok/s

990prefill tok/s

32Kcontext

Tested on a sibling · Sep 26, 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 GDDR7
Architecture	NVIDIA Blackwell
CUDA cores	5,888
AI TOPS	992

Sources: NVIDIA