RTX 5070 Ti

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 byModelHardware setupTotal memory (GB)RecipeContextDecode (tok/s)Prefill (tok/s)Evidence↑ A–Z

3 configurations · 4 recipes

Gemma 4 26B A4B

RTX 5070 Ti16 GB1 card per machine · 1 machine

TabbyAPIEXL3 3.1 bpw

96.9decode tok/s

1,799prefill tok/s

32Kcontext

Tested on this card · Sep 26, 2026

CommandFull recipe ›

Qwen3.8-27B

RTX 5070 Ti16 GB1 card per machine · 1 machine

Exact recipeexllamav3 · EXL3 2.5 bpw · 172K contextexllamav3 · EXL3 2 bpw · 195K context

—decode tok/s

—prefill tok/s

172Kcontext

Reported by MiaAI-Lab · Sep 10, 2026

CommandFull recipe ›

Qwen3.8-Flash-Next

RTX 5070 Ti16 GB1 card per machine · 1 machine

Host RAM

≥ 55 GB free

Disk

≥ 86 GB NVMe

SGLangEXL3 3.05 bpw

44.1decode tok/s

3,338prefill tok/s

256Kcontext

Tested on this card · Oct 16, 2026

CommandFull 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.

Sources: NVIDIA, NVIDIA (2), newegg, microcenter