Can Phi 3 Medium 14B run on RTX PRO 6000 Blackwell Server Edition 96GB?
YES — Runs Great
Phi 3 Medium 14B needs ~22.4 GB VRAM. RTX PRO 6000 Blackwell Server Edition 96GB has 96.0 GB. With Q4_K_M quantization, expect ~169 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
168.9 tok/s
TTFT
1146 ms
Safe context
128K
Memory
22.4 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 | B | Runs well | 168.9 tok/s | 625 ms | 128K |
| Coding | B | Runs well | 168.9 tok/s | 1146 ms | 128K |
| Agentic Coding | B | Runs well | 168.9 tok/s | 1668 ms | 128K |
| Reasoning | B | Runs well | 168.9 tok/s | 1355 ms | 128K |
| RAG | B | Runs well | 168.9 tok/s | 2085 ms | 128K |
Quantization options
How Phi 3 Medium 14B (14B 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 | 5.5 GB | Low | C50 |
Q3_K_S | 3 | 6.9 GB | Low | C50 |
NVFP4 | 4 |
Get started
Copy-paste commands to run Phi 3 Medium 14B on your machine.
Run
ollama run phi3:medium