Can Phi-4-reasoning-plus 14B run on RTX PRO 6000 Blackwell Server Edition 96GB?
YES — Runs Great
Phi-4-reasoning-plus 14B needs ~22.8 GB VRAM. RTX PRO 6000 Blackwell Server Edition 96GB has 96.0 GB. With Q4_K_M quantization, expect ~161 tok/s.
Operating mode
Choose the run profile you care about
Interactive favors responsiveness, while light API and scale-out lean harder on serving readiness. The fit stays the same, but the recommendation lens changes.
Current mode
Balanced
Balanced for general local use. Keeps the ranking neutral across personal and serving workflows.
Select quantization to explore
Fit status
Runs well
Decode
160.8 tok/s
TTFT
1204 ms
Safe context
33K
Memory
22.8 GB / 96.0 GB
Memory breakdown
See how fast it feels
What limits this setup
This setup is broadly balanced for this model.
No major red flags
This recommendation has enough memory headroom and acceptable estimated speed for the selected workload.
Best improvement path
Performance by workload
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | S | Runs well | 160.8 tok/s | 657 ms | 33K |
| Coding | S | Runs well | 160.8 tok/s | 1204 ms | 33K |
| Agentic Coding | S | Runs well | 160.8 tok/s | 1751 ms | 33K |
| Reasoning | S | Runs well | 160.8 tok/s | 1423 ms | 33K |
| RAG | S | Runs well | 160.8 tok/s | 2189 ms | 33K |
Quantization options
How Phi-4-reasoning-plus 14B (14.699999809265137B params) fits at each quantization level on RTX PRO 6000 Blackwell Server Edition 96GB (96.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 5.7 GB | Low | A79 |
Q3_K_S | 3 | 7.2 GB | Low | A79 |
NVFP4 | 4 | 8.2 GB | Medium | A79 |
Q4_K_M | 4 | 9.0 GB | Medium | A79 |
Q5_K_M | 5 | 10.6 GB | High | A79 |
Q6_K | 6 | 12.1 GB | High | A79 |
Q8_0 | 8 | 15.7 GB | Very High | A80 |
F16Best for your GPU | 16 | 30.1 GB | Maximum | A82 |
Get started
Copy-paste commands to run Phi-4-reasoning-plus 14B on your machine.
Run
ollama run phi4-reasoningYour hardware
