Phi-4 14B needs ~15.2 GB VRAM. Tesla P40 24GB has 24.0 GB. With Q4_K_M quantization, expect ~26 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
25.7 tok/s
TTFT
7534 ms
Safe context
16K
Memory
15.2 GB / 24.0 GB
This setup is broadly balanced for this model.
Older PCIe generation
PCIe 3.0 is workable, but it compounds the penalty when you offload heavily or try to scale across multiple cards.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | A | Runs well | 25.7 tok/s | 4109 ms | 16K |
| Coding | A | Runs well | 25.7 tok/s | 7534 ms | 16K |
| Agentic Coding | A | Runs well | 25.7 tok/s | 10959 ms | 16K |
| Reasoning | A | Runs well | 25.7 tok/s | 8904 ms | 16K |
| RAG | A | Runs well | 25.7 tok/s | 13698 ms | 16K |
How Phi-4 14B (14B params) fits at each quantization level on Tesla P40 24GB (24.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 5.5 GB | Low | A77 |
Q3_K_S | 3 | 6.9 GB | Low | A78 |
NVFP4 | 4 | 7.8 GB | Medium | A79 |
Q4_K_M | 4 | 8.5 GB | Medium | A79 |
Q5_K_M | 5 | 10.1 GB | High | A80 |
Q6_K | 6 | 11.5 GB | High | A81 |
Q8_0Best for your GPU | 8 | 15.0 GB | Very High | A82 |
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 | 30.9 tok/s | |
| Qwen 3.5 27B | 27B | S | 13.4 tok/s | |
| Qwen 3.6 27B | 27B | S | 13.4 tok/s | |
| Qwen3-VL 30B A3B Instruct | 30B | S | 31.9 tok/s | |
| Qwen 3.5 35B A3B | 35B | A | 16.7 tok/s |
Yes, Tesla P40 24GB can run Phi-4 14B with a A grade (Runs well). Expected decode speed: 25.7 tok/s.
Phi-4 14B (14B parameters) requires approximately 15.2 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 Tesla P40 24GB, Phi-4 14B achieves approximately 25.7 tokens per second decode speed with a time-to-first-token of 7534ms using Q4_K_M quantization.
For coding workloads, Phi-4 14B on Tesla P40 24GB receives a A grade with 25.7 tok/s and 16K context.
On Tesla P40 24GB, 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-tesla-p40-24gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: