RTX PRO 6000 Blackwell Max-Q Workstation Edition × Qwen2.5 14B Instruct
Qwen2.5 14B Instruct on RTX PRO 6000 Blackwell Max-Q Workstation Edition
25.9best gen tok/s
3,061best prompt tok/s
640max context tested
5results
Measured · all numbers below come from the linked sources
llama.cpp
| Quant | Gen tok/s | Prompt tok/s | Source | Context tested | TTFT | Build |
|---|---|---|---|---|---|---|
| Q4_K - Medium | 25.9 | 3,061 | LocalScore ↗ | 512+128 | 414 ms | llamafile 0.9.2 |
| Q4_K - Medium | 24.9 | 2,735 | LocalScore ↗ | 512+128 | 451 ms | llamafile 0.9.2 |
| Q4_K - Medium | 23.2 | 2,256 | LocalScore ↗ | 512+128 | 580 ms | llamafile 0.9.2 |
| Q4_K - Medium | 23.1 | 2,118 | LocalScore ↗ | 512+128 | 837 ms | llamafile 0.9.2 |
| Q4_K - Medium | 21.5 | 2,942 | LocalScore ↗ | 512+128 | 437 ms | llamafile 0.9.2 |
Ollama
No measured Ollama results yet. Submit yours →
MLX
No measured MLX results yet. Submit yours →
"Context tested" is the largest prompt+generation length actually benchmarked (tokens), not a memory-fit estimate.
What else can RTX PRO 6000 Blackwell Max-Q Workstation Edition run? →
Includes results from LocalScore, a Mozilla Builders project by cjpais, mirrored in the cn0303/local-llm-speed-benchmarks dataset. LocalScore runs use llamafile, which is built on llama.cpp.