Phi 3 Medium 14B needs ~17.3 GB VRAM. NVIDIA L40 48GB has 48.0 GB. With Q4_K_M quantization, expect ~89 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
89.1 tok/s
TTFT
2173 ms
Safe context
128K
Memory
17.3 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 | 89.1 tok/s | 1186 ms | 128K |
| Coding | B | Runs well | 89.1 tok/s | 2173 ms | 128K |
| Agentic Coding | B | Runs well | 89.1 tok/s | 3161 ms | 128K |
| Reasoning | B | Runs well | 89.1 tok/s | 2569 ms | 128K |
| RAG | B | Runs well | 89.1 tok/s | 3952 ms | 128K |
How Phi 3 Medium 14B (14B params) fits at each quantization level on NVIDIA L40 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, NVIDIA L40 48GB can run Phi 3 Medium 14B with a B grade (Runs well). Expected decode speed: 89.1 tok/s.
Phi 3 Medium 14B (14B parameters) requires approximately 17.3 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 NVIDIA L40 48GB, Phi 3 Medium 14B achieves approximately 89.1 tokens per second decode speed with a time-to-first-token of 2173ms using Q4_K_M quantization.
For coding workloads, Phi 3 Medium 14B on NVIDIA L40 48GB receives a B grade with 89.1 tok/s and 128K context.
On NVIDIA L40 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-l40-48gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: