Phi-4-reasoning-plus 14B needs ~15.6 GB VRAM. Tesla P40 24GB has 24.0 GB. With Q4_K_M quantization, expect ~25 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
24.5 tok/s
TTFT
7911 ms
Safe context
33K
Memory
15.6 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 | S | Runs well | 24.5 tok/s | 4315 ms | 33K |
| Coding | S | Runs well | 24.5 tok/s | 7911 ms | 33K |
| Agentic Coding | S | Runs well | 24.5 tok/s | 11506 ms | 33K |
| Reasoning | S | Runs well | 24.5 tok/s | 9349 ms | 33K |
| RAG | S | Runs well | 24.5 tok/s | 14383 ms | 33K |
Inference speed
Estimated decode speed (tokens/sec) for Phi-4-reasoning-plus 14B at Q4_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is RTX 5090 32GB at ~144 tok/s. Speed is memory-bandwidth bound, so cards that fit the whole model in VRAM run far faster than ones that offload to system RAM.
| GPU / Mac | Memory | Quant | Speed (tok/s) | Fits? |
|---|---|---|---|---|
 RTX 5090 32GB | 32 GB | Q4_K_M | 143.9 | Fits |
| RTX 4090 24GB | 24 GB | Q4_K_M | 91.8 | Fits |
RX 7900 XTX 24GB | 24 GB | Q4_K_M | 82.9 | Fits |
| RTX 3090 24GB | 24 GB | Q4_K_M | 78.5 | Fits |
| RTX 4080 Super 16GB | 16 GB | Q4_K_M | 75.5 | Tight |
Mac Studio M3 Ultra 256GB | 256 GB | Q4_K_M | 66.8 | Fits |
Mac Studio M2 Ultra 128GB | 128 GB | Q4_K_M | 55.6 | Fits |
Mac Studio M1 Ultra 128GB | 128 GB | Q4_K_M | 52.7 | Fits |
MacBook Pro M4 Max 128GB | 128 GB | Q4_K_M | 37.6 | Fits |
MacBook Pro M4 Max 64GB | 64 GB | Q4_K_M | 37.6 | Fits |
MacBook Pro M3 Max 64GB | 64 GB | Q4_K_M | 28.8 | Fits |
MacBook Pro M1 Max 64GB | 64 GB | Q4_K_M | 26.4 | Fits |
| RTX 4070 12GB | 12 GB | Q4_K_M | 24.9 | Heavy offload |
MacBook Pro M4 Pro 48GB | 48 GB | Q4_K_M | 23.0 | Fits |
| RTX 3060 12GB | 12 GB | Q4_K_M | 14.6 | Heavy offload |
| RTX 4060 8GB | 8 GB | Q4_K_M | 5.5 | Too big |
Estimates for single-stream decoding at Q4_K_M; real tokens/sec varies with prompt length, context, batch size, and runtime build. Prompt processing (prefill) is faster than the decode figures shown here.
How Phi-4-reasoning-plus 14B (14.699999809265137B params) fits at each quantization level on Tesla P40 24GB (24.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 5.7 GB | Low | S86 |
Q3_K_S | 3 | 7.2 GB | Low | S86 |
NVFP4 | 4 | 8.2 GB | Medium | S87 |
Q4_K_M | 4 | 9.0 GB | Medium | S88 |
Q5_K_M | 5 | 10.6 GB | High | S89 |
Q6_K | 6 | 12.1 GB | High | S90 |
Q8_0Best for your GPU | 8 | 15.7 GB | Very High | S90 |
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 | 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-reasoning-plus 14B with a S grade (Runs well). Expected decode speed: 24.5 tok/s.
Phi-4-reasoning-plus 14B (14.699999809265137B parameters) requires approximately 15.6 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 Tesla P40 24GB, Phi-4-reasoning-plus 14B achieves approximately 24.5 tokens per second decode speed with a time-to-first-token of 7911ms using Q4_K_M quantization.
For coding workloads, Phi-4-reasoning-plus 14B on Tesla P40 24GB receives a S grade with 24.5 tok/s and 33K context.
On Tesla P40 24GB, 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-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: