Phi-4 14B needs ~17.3 GB VRAM. NVIDIA L20 48GB has 48.0 GB. With Q4_K_M quantization, expect ~83 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
83.4 tok/s
TTFT
2322 ms
Safe context
16K
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 | A | Runs well | 83.4 tok/s | 1267 ms | 16K |
| Coding | A | Runs well | 83.4 tok/s | 2322 ms | 16K |
| Agentic Coding | A | Runs well | 83.4 tok/s | 3378 ms | 16K |
| Reasoning | A | Runs well | 83.4 tok/s | 2745 ms | 16K |
| RAG | A | Runs well | 83.4 tok/s | 4222 ms | 16K |
How Phi-4 14B (14B params) fits at each quantization level on NVIDIA L20 48GB (48.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 5.5 GB | Low | A73 |
Q3_K_S | 3 | 6.9 GB | Low | A74 |
NVFP4 | 4 | 7.8 GB | Medium | A74 |
Q4_K_M | 4 | 8.5 GB | Medium | A74 |
Q5_K_M | 5 | 10.1 GB | High | A74 |
Q6_K | 6 | 11.5 GB | High | A75 |
Q8_0 | 8 | 15.0 GB | Very High | A76 |
F16Best for your GPU | 16 | 28.7 GB | Maximum | A80 |
Copy-paste commands to run Phi-4 14B on your machine.
Run
ollama run phi4Your hardware
| Model | Params | Grade | Decode | Capabilities |
|---|---|---|---|---|
 Qwen3-Coder 30B A3B Instruct | 30.5B | S | 68.7 tok/s | |
| Qwen 3.5 27B | 27B | S | 28.6 tok/s | |
| Qwen 3.6 27B | 27B | S | 18.8 tok/s | |
| Qwen 3.6 35B A3B | 35B | S | 85.8 tok/s | |
| Qwen3-VL 30B A3B Instruct | 30B | S | 98.6 tok/s |
Yes, NVIDIA L20 48GB can run Phi-4 14B with a A grade (Runs well). Expected decode speed: 83.4 tok/s.
Phi-4 14B (14B parameters) requires approximately 17.3 GB of memory with Q4_K_M quantization.
The recommended quantization for Phi-4 14B is Q4_K_M, which balances quality and memory efficiency.
On NVIDIA L20 48GB, Phi-4 14B achieves approximately 83.4 tokens per second decode speed with a time-to-first-token of 2322ms using Q4_K_M quantization.
For coding workloads, Phi-4 14B on NVIDIA L20 48GB receives a A grade with 83.4 tok/s and 16K context.
On NVIDIA L20 48GB, Phi-4 14B can safely use up to 16K tokens of context. The model's official context limit is 16K, 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-4-14b-on-l20-48gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: