Phi 3 Medium 14B needs ~17.6 GB VRAM. RTX 6000 Ada 48GB has 48.0 GB. With Q4_K_M quantization, expect ~99 tok/s.
Operating mode
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
99.1 tok/s
TTFT
1954 ms
Safe context
128K
Memory
17.6 GB / 48.0 GB
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.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | B | Runs well | 99.1 tok/s | 1066 ms | 128K |
| Coding | B | Runs well | 99.1 tok/s | 1954 ms | 128K |
| Agentic Coding | B | Runs well | 99.1 tok/s | 2842 ms | 128K |
| Reasoning | B | Runs well | 99.1 tok/s | 2309 ms | 128K |
| RAG | B | Runs well | 99.1 tok/s | 3552 ms | 128K |
How Phi 3 Medium 14B (14B params) fits at each quantization level on RTX 6000 Ada 48GB (48.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 5.5 GB | Low | C53 |
Q3_K_S | 3 | 6.9 GB | Low | C53 |
NVFP4 | 4 | 7.8 GB | Medium | C53 |
Q4_K_M | 4 | 8.5 GB | Medium | C53 |
Q5_K_M | 5 | 10.1 GB | High | C54 |
Q6_K | 6 | 11.5 GB | High | C54 |
Q8_0 | 8 | 15.0 GB | Very High | B55 |
F16Best for your GPU | 16 | 28.7 GB | Maximum | B59 |
Copy-paste commands to run Phi 3 Medium 14B on your machine.
Run
ollama run phi3:mediumYes, RTX 6000 Ada 48GB can run Phi 3 Medium 14B with a B grade (Runs well). Expected decode speed: 99.1 tok/s.
Phi 3 Medium 14B (14B parameters) requires approximately 17.6 GB of memory with Q4_K_M quantization.
The recommended quantization for Phi 3 Medium 14B is Q4_K_M, which balances quality and memory efficiency.
On RTX 6000 Ada 48GB, Phi 3 Medium 14B achieves approximately 99.1 tokens per second decode speed with a time-to-first-token of 1954ms using Q4_K_M quantization.
For coding workloads, Phi 3 Medium 14B on RTX 6000 Ada 48GB receives a B grade with 99.1 tok/s and 128K context.
On RTX 6000 Ada 48GB, Phi 3 Medium 14B can safely use up to 128K tokens of context. The model's official context limit is 128K, but available memory constrains the safe maximum.
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/phi-3-medium-14b-on-rtx-6000-ada-48gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: