RTX 4000 Ada

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

4 configurations · 4 recipes

Gemma 4 26B A4B

RTX 4000 Ada20 GB1 card per machine · 1 machine

TabbyAPIEXL3 3.1 bpw

68.8decode tok/s

1,598prefill tok/s

32Kcontext

Tested on this card · Sep 27, 2026

CommandFull recipe ›

LFM2.5-2.6B

RTX 4000 Ada20 GB1 card per machine · 1 machine

SGLangFormat not recorded

—decode tok/s

—prefill tok/s

128Kcontext

Earlier check · Date not recorded

CommandFull recipe ›

Qwen3.5-9B

RTX 4000 Ada20 GB1 card per machine · 1 machine

TabbyAPIEXL3 4 bpw

89.9decode tok/s

—prefill tok/s

256Kcontext

Earlier check · Sep 23, 2026

CommandFull recipe ›

Qwen3.8-27B

RTX 4000 Ada20 GB1 card per machine · 1 machine

TabbyAPIEXL3 4 bpw

15.5decode tok/s

361prefill tok/s

128Kcontext

Tested on this card · Sep 27, 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)