Fastest & Best quality
Qwen3.8-27B-UD-Q6_K_XL
27B
90.1 tok/sQuality 88.6
Highest token generation speed at 90.1 tok/s. Highest completed quality score at 88.6.
Hardware Benchmarks
Best Local LLM Performance for RTX Pro 6000 Blackwell Max Q Workstation Edition
Compare RTX Pro 6000 Blackwell Max Q Workstation Edition benchmark results and see which models actually earn the best completed quality scores.
Hardware Overview
GPU-specific specifications for local LLM planning.
- VRAM
- 96GB
Recommended Models
Models we recommend for RTX Pro 6000 Blackwell Max Q Workstation Edition.
Frequently asked questions
Which models actually run best on the RTX Pro 6000 Blackwell Max Q Workstation Edition, by task, from community benchmark data.
- What is the best local model for coding on the RTX Pro 6000 Blackwell Max Q Workstation Edition?
- On the RTX Pro 6000 Blackwell Max Q Workstation Edition, Qwen3.8-27B-UD-Q6_K_XL ranks first for coding in our benchmarks (75.9/100 at ~84.3 tok/s).
- What is the best local model for agentic workflows on the RTX Pro 6000 Blackwell Max Q Workstation Edition?
- On the RTX Pro 6000 Blackwell Max Q Workstation Edition, Qwen3.8-27B-UD-Q6_K_XL ranks first for agentic workflows in our benchmarks (76.9/100 at ~84.3 tok/s).
Benchmark Results
Completed quality-ranked benchmark results for NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition.