Phi 3 Medium 14B needs ~16.0 GB VRAM. RTX 5090 32GB has 32.0 GB. With Q4_K_M quantization, expect ~151 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
151.1 tok/s
TTFT
1281 ms
Safe context
100K
Memory
16.0 GB / 32.0 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 | 151.1 tok/s | 699 ms | 100K |
| Coding | B | Runs well | 151.1 tok/s | 1281 ms | 100K |
| Agentic Coding | B | Runs well | 151.1 tok/s | 1863 ms | 100K |
| Reasoning | B | Runs well | 151.1 tok/s | 1514 ms | 100K |
| RAG | B | Runs well | 151.1 tok/s | 2329 ms | 100K |
How Phi 3 Medium 14B (14B params) fits at each quantization level on RTX 5090 32GB (32.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 5.5 GB | Low | C55 |
Q3_K_S | 3 | 6.9 GB | Low | B55 |
NVFP4 | 4 | 7.8 GB | Medium | B56 |
Q4_K_M | 4 | 8.5 GB | Medium | B56 |
Q5_K_M | 5 | 10.1 GB | High | B57 |
Q6_K | 6 | 11.5 GB | High | B57 |
Q8_0Best for your GPU | 8 | 15.0 GB | Very High | B59 |
F16 | 16 | 28.7 GB | Maximum | F0 |
Copy-paste commands to run Phi 3 Medium 14B on your machine.
Run
ollama run phi3:mediumYes, RTX 5090 32GB can run Phi 3 Medium 14B with a B grade (Runs well). Expected decode speed: 151.1 tok/s.
Phi 3 Medium 14B (14B parameters) requires approximately 16.0 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 5090 32GB, Phi 3 Medium 14B achieves approximately 151.1 tokens per second decode speed with a time-to-first-token of 1281ms using Q4_K_M quantization.
For coding workloads, Phi 3 Medium 14B on RTX 5090 32GB receives a B grade with 151.1 tok/s and 100K context.
On RTX 5090 32GB, Phi 3 Medium 14B can safely use up to 100K 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-5090-32gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: