Phi-4-reasoning-plus 14B needs ~16.4 GB VRAM. RTX 5090 32GB has 32.0 GB. With Q4_K_M quantization, expect ~144 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
143.9 tok/s
TTFT
1345 ms
Safe context
33K
Memory
16.4 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 | S | Runs well | 143.9 tok/s | 734 ms | 33K |
| Coding | S | Runs well | 143.9 tok/s | 1345 ms | 33K |
| Agentic Coding | S | Runs well | 143.9 tok/s | 1956 ms | 33K |
| Reasoning | S | Runs well | 143.9 tok/s | 1590 ms | 33K |
| RAG | S | Runs well | 143.9 tok/s | 2446 ms | 33K |
How Phi-4-reasoning-plus 14B (14.699999809265137B params) fits at each quantization level on RTX 5090 32GB (32.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 5.7 GB | Low | A84 |
Q3_K_S | 3 | 7.2 GB | Low | A84 |
NVFP4 | 4 | 8.2 GB | Medium | A85 |
Q4_K_M | 4 | 9.0 GB | Medium | S85 |
Q5_K_M | 5 | 10.6 GB | High | S86 |
Q6_K | 6 | 12.1 GB | High | S87 |
Q8_0Best for your GPU | 8 | 15.7 GB | Very High | S88 |
F16 | 16 | 30.1 GB | Maximum | F0 |
Copy-paste commands to run Phi-4-reasoning-plus 14B on your machine.
Run
ollama run phi4-reasoningYour hardware
| Model | Params | Grade | Decode | Capabilities |
|---|---|---|---|---|
 Qwen3-Coder 30B A3B Instruct | 30.5B | S | 181.6 tok/s | |
| Qwen 3.5 27B | 27B | S | 78.7 tok/s | |
| Qwen 3.6 27B | 27B | S | 79 tok/s | |
| Qwen 3.6 35B A3B | 35B | S | 128.2 tok/s | |
| Qwen3-VL 30B A3B Instruct | 30B | S | 187.8 tok/s |
Yes, RTX 5090 32GB can run Phi-4-reasoning-plus 14B with a S grade (Runs well). Expected decode speed: 143.9 tok/s.
Phi-4-reasoning-plus 14B (14.699999809265137B parameters) requires approximately 16.4 GB of memory with Q4_K_M quantization.
The recommended quantization for Phi-4-reasoning-plus 14B is Q4_K_M, which balances quality and memory efficiency.
On RTX 5090 32GB, Phi-4-reasoning-plus 14B achieves approximately 143.9 tokens per second decode speed with a time-to-first-token of 1345ms using Q4_K_M quantization.
For coding workloads, Phi-4-reasoning-plus 14B on RTX 5090 32GB receives a S grade with 143.9 tok/s and 33K context.
On RTX 5090 32GB, Phi-4-reasoning-plus 14B can safely use up to 33K tokens of context. The model's official context limit is 33K, 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-reasoning-plus-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: