RTX 6000 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 · 5 recipes

Gemma 4 26B A4B

RTX 6000 Ada48 GB1 card per machine · 1 machine

TabbyAPIEXL3 6.1 bpw

128.6decode tok/s

3,541prefill tok/s

128Kcontext

Tested on this card · Sep 26, 2026

CommandFull recipe ›

Nemotron 3.5 Lightning 30B-A3B

RTX 6000 Ada48 GB1 card per machine · 1 machine

SGLangNVFP4

—decode tok/s

—prefill tok/s

1024Kcontext

Reported by MiaAI-Lab · Aug 11, 2026

CommandFull recipe ›

Qwen3.6-35B-A3B

RTX 6000 Ada48 GB1 card per machine · 1 machine

SGLangFP8

140.5decode tok/s

6,641prefill tok/s

128Kcontext

Tested on this card · Sep 26, 2026

CommandFull recipe ›

Qwen3.8-27B

RTX 6000 Ada48 GB1 card per machine · 1 machine

Exact recipesglang · FP8 · 96K contexttabbyapi · EXL3 5 bpw · 256K context

22.9decode tok/s

1,822prefill tok/s

96Kcontext

Tested on this card · Sep 26, 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, bhphotovideo, NVIDIA (2)