Phi-4 14B needs ~16.0 GB VRAM. NVIDIA V100 32GB has 32.0 GB. With Q4_K_M quantization, expect ~76 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
75.9 tok/s
TTFT
2551 ms
Safe context
16K
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 | A | Runs well | 75.9 tok/s | 1391 ms | 16K |
| Coding | A | Runs well | 75.9 tok/s | 2551 ms | 16K |
| Agentic Coding | S | Runs well | 75.9 tok/s | 3710 ms | 16K |
| Reasoning | A | Runs well | 75.9 tok/s | 3014 ms | 16K |
| RAG | S | Runs well | 75.9 tok/s | 4637 ms | 16K |
How Phi-4 14B (14B params) fits at each quantization level on NVIDIA V100 32GB (32.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 5.5 GB | Low | A76 |
Q3_K_S | 3 | 6.9 GB | Low | A76 |
NVFP4 | 4 | 7.8 GB | Medium | A76 |
Q4_K_M | 4 | 8.5 GB | Medium | A77 |
Q5_K_M | 5 | 10.1 GB | High | A77 |
Q6_K | 6 | 11.5 GB | High | A78 |
Q8_0Best for your GPU | 8 | 15.0 GB | Very High | A80 |
F16 | 16 | 28.7 GB | Maximum | F0 |
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 | 91.2 tok/s | |
| Qwen 3.5 27B | 27B | S | 39.5 tok/s | |
| Qwen 3.6 27B | 27B | S | 39.7 tok/s | |
| Qwen 3.6 35B A3B | 35B | S | 76.6 tok/s | |
| Qwen3-VL 30B A3B Instruct | 30B | S | 94.3 tok/s |
Yes, NVIDIA V100 32GB can run Phi-4 14B with a A grade (Runs well). Expected decode speed: 75.9 tok/s.
Phi-4 14B (14B parameters) requires approximately 16.0 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 V100 32GB, Phi-4 14B achieves approximately 75.9 tokens per second decode speed with a time-to-first-token of 2551ms using Q4_K_M quantization.
For coding workloads, Phi-4 14B on NVIDIA V100 32GB receives a A grade with 75.9 tok/s and 16K context.
On NVIDIA V100 32GB, 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-v100-32gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: