RTX PRO 6000 Blackwell

NVIDIA · 96 GB · 1792 GB/s

Top 3 recipes

Recommended

Qwen3.8-Flash-Next

EXL3 2.05 bpwTabbyAPI128K context

Best for The most capable model a single 96 GB card runs.

165 tok/sdecode

4,722 tok/sprefill

128Kcontext

✓ Thinks✓ Tools✓ Long context✓ Vision

Tested on this card · Sep 26, 2026

Longest context

Qwen3.8-27B

EXL3 6 bpwTabbyAPI256K context

Best for Coding agents, long documents, everyday assistant work.

52 tok/sdecode

568 tok/sprefill

256Kcontext

✓ Thinks✓ Tools✓ Long context✓ Vision

Tested on this card · Sep 25, 2026

Fastest

Qwen3.5-9B

EXL3 8 bpwTabbyAPI256K context

Best for Fast answers and light agent work on 8–12 GB cards.

229 tok/sdecode

4,854 tok/sprefill

256Kcontext

✓ Thinks✓ Tools✓ Long context

Tested on this card · Sep 26, 2026